# Qwen3.8

Qwen3.8 · دیگر در رصد فعال نیست. انتشار یا تغییر نام با این نام تأیید نشده است.

- توسعه‌دهنده: Alibaba
- Id: qwen3.8
- طبق گزارش‌ها: 2026-03-31T00:30:28.000Z
- وضعیت: طبق گزارش‌ها
- دیگر در رصد فعال نیست. انتشار یا تغییر نام با این نام تأیید نشده است.
- اصلی: https://alexgetman.com/fa/models/alibaba/qwen3-8/

## پرسش‌ها

### Qwen3.8 چه زمانی عرضه شد؟

تاریخ عرضه نامشخص

## خط زمانی

- 2026-07-19T11:07:11.687Z · [Alex Getman](https://alexgetman.com/86/alibaba-just-teased-qwen3-8-with-2-4t-parameters/)
> Alibaba just teased Qwen3.8 with 2.4T parameters
> 
> This is the new Qwen flagship, with open weights coming soon. Alibaba ranks it right below Claude Fable 5. Public benchmarks are still missing, so nobody really knows how close it actually is to Fable, or how it stacks up against GPT-5.6 Sol and Kimi K3.
> 
> Pricing is the fun part. Kimi K3 costs $3/$15, so Qwen3.8 will probably land in the same range.
> 
> The preview is already live in Qoder. It uses 10x fewer credits during the day and 50x fewer at night, so you can basically test it for free.
- 2026-08-14T18:14:16.552Z · [Alex Getman](https://alexgetman.com/184/alibaba-open-sourced-qwen3-8/)
> ⚡️ Alibaba released Qwen3.8’s weights
> 
> A model at Claude Opus 4.6 level, a flagship just six months ago, can now run on a single RTX 4090. Qwen3.8 27B uses around 17 GB of VRAM when quantized and should deliver ~50 tok/s.
- 2026-08-18T05:00:00.000Z · [Alex Getman](https://alexgetman.com/196/qwen-3-8-27b-beat-gpt-5-6-terra/)
> ⚡️ Qwen 3.8 27B beat GPT 5.6 Terra
> 
> This happened in the AA Agentic Index, a benchmark that tests how well models handle agentic tasks. And you can run Qwen 3.8 27B locally on a single RTX 3090.
- 2026-08-26T11:23:48.753Z · [Alex Getman](https://alexgetman.com/356/qwen3-8-flash-next-drops-today/)
> 🚨 QWEN3.8 FLASH NEXT DROPS TODAY
> 
> A ModelScope description that was quickly taken down reportedly revealed:
> 
> • 125B main parameters
> • 51B N gram embeddings
> • Only 6B active per token
> • Multimodal MoE architecture
> 
> The model is also an official preview of the upcoming Qwen4 architecture.
- 2026-08-26T12:54:00.791Z · [Alex Getman](https://alexgetman.com/357/qwen3-8-flash-next-is-out/)
> 🚨 QWEN3.8 FLASH NEXT IS OUT
> 
> The leaked specs were real:
> • 125B multimodal MoE
> • Only 6B active
> • 262K native context, up to 1M
> 
> Qwen says it beats Claude Opus 4.6 across coding, agentic tasks, tool use and several multimodal benchmarks.
- 2026-09-17T18:25:45.043Z · [Alex Getman](https://alexgetman.com/428/qwen3-8-omni-flash-is-out/)
> 🚨 Qwen3.8 Omni Flash is out
> 
> It can see, hear and understand video, then actually act on it
> 
> Give it hours of footage and it can find the right moments, translate, edit or turn it into notes. Give it a meeting and it can pull out tasks and start working on them
> 
> 1M context, API from $0.43
- 2026-11-05T17:57:47.304Z · [GitHub · QwenLM/qwen-code · PR](https://github.com/QwenLM/qwen-code/pull/15184)
> - The Standard preset has the same qwen3.8 effort and GLM thinking gaps and will be aligned in a follow-up
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · 0xburden/modelship · @0xburden](https://github.com/0xburden/modelship/pull/8)
> - Reviewed immutable catalog of 25 standalone Qwen3.8 GGUF quantizations; wizard displays sizes, numeric/letter/full-value selection and a visible UD-Q4_K_M default. No hardware-driven quant substitution; flags
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · Azure/azureml-assets · @hanbitmyths](https://github.com/Azure/azureml-assets/pull/5452)
> Add MAI, Qwen3.8 and Nemotron 3.5 Foundry Local coding models
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · BuQQzz/SHIELD2.0 · @BuQQzz](https://github.com/BuQQzz/SHIELD2.0/pull/56)
> Makes Qwen3.8 27B (IQ1_M) a working coding model on an 8 GB card (RTX 2070 SUPER) through SHIELD's own llama-server.
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · FlashML-org/FreeToken · @zihaomu](https://github.com/FlashML-org/FreeToken/pull/897)
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · IBM/Evoflux · @renovate[bot]](https://github.com/IBM/Evoflux/pull/11)
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · NVIDIA/hyperflare-inference · @Raydius](https://github.com/NVIDIA/hyperflare-inference/pull/212)
> The pinned Qwen3.8 Flash Next checkpoint trains a 262,144-token context (theta 10M, interleaved MRoPE 11/11/10). This adds a declared serving variant of the same weights
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · SceneWorks/SceneWorks · @michaeltrefry](https://github.com/SceneWorks/SceneWorks/pull/3383)
> SW-7119: Qwen3.8 27B describer model and tier in core, worker, API and catalog
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · michsindlinger/specwright · @michsindlinger](https://github.com/michsindlinger/specwright/pull/125)
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · nearai/cvm-compose-files · @PierreLeGuen](https://github.com/nearai/cvm-compose-files/pull/488)
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/2629)
> [Model][Qwen3.8] QSA main-KV decode context parallelism over rank pairs (DCP-2) kernels
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/2895)
> [Model][Qwen3.8] Qwen3.8-Flash model and registration hooks
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3232)
> [Model][Qwen3.8] QSA union-walk kernels (plan, dense, SparseCore gather, prefill)
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3233)
> [Model][Qwen3.8] QSA KV write kernels (fused, main, compressed)
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3234)
> [Model][Qwen3.8] Pooled QSA kernel over the unified KV pool
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3235)
> [Model][Qwen3.8] Hyper-connection kernels
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3236)
> [Model][Qwen3.8] PLE lookup and gate kernels
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3237)
> [Model][Qwen3.8] Unified KV pool kernels
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3238)
> [Model][Qwen3.8] GDN input preparation kernel
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3239)
> [Model][Qwen3.8] Torch bridge for the QSA kernels
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3240)
> [Model][Qwen3.8] QSA Torch-to-JAX ops
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3241)
> [Model][Qwen3.8] PLE Torch-to-JAX ops
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3242)
> [Model][Qwen3.8] In-place rows update op
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3243)
> [Model][Qwen3.8] Mamba tail fold: export prefill checkpoints from inside the step
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3244)
> [Model][Qwen3.8] Per-group Mamba index accessors
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3245)
> [Model][Qwen3.8] Model-owned GDN op and layer (no register_oot)
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3246)
> [Model][Qwen3.8] QSA attention layer
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3247)
> [Model][Qwen3.8] Sequence-parallel prefill backbone
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3248)
> [Model][Qwen3.8] PLE feature: tables, host lookup, storage, offload and pooled PLE
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3249)
> [Model][Qwen3.8] Config hook, geometry checks and pooled cache layout
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3250)
> [Model][Qwen3.8] PD transfer: identity, manifest and Raiden connector
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3251)
> [Model][Qwen3.8] Pooled KV cache materialization
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3252)
> [Model][Qwen3.8] GDN layer input preparation
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3253)
> [Model][Qwen3.8] Hyper-connection layers
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3254)
> [Model][Qwen3.8] Runner input adapter
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3255)
> [Model][Qwen3.8] KV offload pool regions
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3256)
> [Model][Qwen3.8] MTP draft model
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3267)
> [Model][Qwen3.8] qwen38_flash package entry: register() and READMEs
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · xadupre/devdash-agents · @xadupre](https://github.com/xadupre/devdash-agents/pull/19)
> - Real Qwen3.8 27B on H200-101, physical CUDA 7: streaming generation and a follow-up turn succeeded. Used a temporary configuration with 16 KV blocks and
- 2026-11-13T19:07:40.219Z · [GitHub search · Alibaba · commits · Azure/azureml-assets · @hanbitmyths](https://github.com/Azure/azureml-assets/commit/229f9a3bd592035925db8d0a49fd65f8b5c43998)
> Add MAI, Qwen3.8 and Nemotron 3.5 Foundry Local coding models (#5452)
- 2026-11-13T19:07:40.219Z · [GitHub search · Alibaba · commits · Hallo-ich-bin-PeppaPig/Singularity · @Hallo-ich-bin-PeppaPig](https://github.com/Hallo-ich-bin-PeppaPig/Singularity/commit/b33219c6ead9582f7e03467b2d6885718bbe16cc)
- 2026-11-13T19:07:40.219Z · [GitHub search · Alibaba · commits · QuantumKuba/Diffactly · @QuantumKuba](https://github.com/QuantumKuba/Diffactly/commit/77529540c23a8e7419a0147263f52ad0078ae3df)
- 2026-11-13T19:07:40.219Z · [GitHub search · Alibaba · commits · aabhay007/Personal-AI-Core · @aabhay007](https://github.com/aabhay007/Personal-AI-Core/commit/54e756490e80be233ca0314f9fed50baad560413)
- 2026-11-13T19:07:40.219Z · [GitHub search · Alibaba · commits · agentgateway/agentgateway · @github-actions[bot]](https://github.com/agentgateway/agentgateway/commit/b7f833ec371abdb5a58fe64c9a7409a51cd1d11c)
> json.providers.nebius.models["Qwen/Qwen3.8-27B"].name = "Qwen3.8 27B";
- 2026-11-13T19:07:40.219Z · [GitHub search · Alibaba · commits · fdietze/pi-infinite-context · @fdietze](https://github.com/fdietze/pi-infinite-context/commit/af207012a9c5522c75abcf01352ef15b166e983c)
- 2026-11-13T19:07:40.219Z · [GitHub search · Alibaba · commits · finereli/pyramid-mcp · @finereli](https://github.com/finereli/pyramid-mcp/commit/279f60c731b0ee6d5fe2b68bb2cfe24b97358c64)
- 2026-11-13T19:07:40.219Z · [GitHub search · Alibaba · commits · onprem-ai/deployment-catalog · @tomas-polach](https://github.com/onprem-ai/deployment-catalog/commit/13545a9aa19112ab1251fe153caa0cf872afddc1)
- 2026-11-15T10:44:56.887Z · [GitHub search · Alibaba · pulls · Finkregh/stepstone-hierarchy · @renovate[bot]](https://github.com/Finkregh/stepstone-hierarchy/pull/11)
> using catalog metadata, with verified DeepSeek V4 and Qwen3.8 fallbacks and removal of redundant GLM 5.2 and Kimi K3 effort aliases ([#​9323](https://redirect.github.com/earendil-works/pi/issues/9323)).
- 2026-11-15T10:44:56.887Z · [GitHub search · Alibaba · pulls · celve/miles · @celve](https://github.com/celve/miles/pull/46)
- 2026-11-15T10:44:56.887Z · [GitHub search · Alibaba · pulls · copse-dev/agent-pane · @jonathanKingston](https://github.com/copse-dev/agent-pane/pull/4294)
> Copse, agent mode/default Guardian → native LM Studio Qwen3.8 guest.** All15 full raw guest frames were independently opened; a separate read-only reviewer checked the same
- 2026-11-15T10:44:56.887Z · [GitHub search · Alibaba · pulls · engeldlgado/toshllm · @andruwa13](https://github.com/engeldlgado/toshllm/pull/165)
> downloaded from Hugging Face, the repository name (e.g., `empero-ai/Qwen3.8-35B-A3B-Distill-GGUF` → `Qwen3.8 35B-A3B`) is used as the primary title source instead of generic GGUF metadata headers
- 2026-11-15T10:44:56.887Z · [GitHub search · Alibaba · pulls · radixark/miles · @celve](https://github.com/radixark/miles/pull/4857)
- 2026-11-15T11:04:05.733Z · [GitHub search · Alibaba · pulls · logicplanes/kaeso · @dvnold](https://github.com/logicplanes/kaeso/pull/1109)
- 2026-11-15T11:04:05.733Z · [GitHub search · Alibaba · pulls · orioli/IM-LLM · @Mihawii](https://github.com/orioli/IM-LLM/pull/1)
> three models from Chinese labs: DeepSeek V4.1 Flash, Qwen3.8 Flash and DeepSeek V4 Pro. It also checks the judge and breaks down what everything cost.
- 2026-11-15T11:04:05.733Z · [GitHub search · Alibaba · pulls · siddsachar/row-bot · @siddsachar](https://github.com/siddsachar/row-bot/pull/898)
> - The only local model is the stock `qwen3.8:27b`. Its Ollama tag, digest and details are recorded in each run's config. Personal fine-tunes and `gpt-oss:20b`
- 2026-11-15T11:04:05.733Z · [GitHub search · Alibaba · pulls · slimsami/strycast · @slimsami](https://github.com/slimsami/strycast/pull/71)
- 2026-11-15T11:04:35.339Z · [GitHub search · Alibaba · commits · logicplanes/kaeso · @dvnold](https://github.com/logicplanes/kaeso/commit/3d742a5cd4e6b39f902b3dec668377e394559c74)
> "reasoning_content"])` (GPT OSS sends both, Qwen3.8 only `reasoning`).
- 2026-11-15T11:27:38.504Z · [GitHub search · Alibaba · pulls · alondigitized/ai-files · @alondigitized](https://github.com/alondigitized/ai-files/pull/104)
> **Angle:** Qwen3.8's reasoning said "without tool calls," and in the same turn it ran a shell command that tried to upload a test string to
- 2026-11-15T11:28:06.809Z · [GitHub search · Alibaba · commits · saumen/llama-server-launcher · @saumen](https://github.com/saumen/llama-server-launcher/commit/3406f69992a621de1850b391896294d569703f20)
> chore: Update Qwen3.8 to Q6_K_M and bump llama.cpp default tag
- 2026-11-15T11:44:00.590Z · [GitHub search · Alibaba · pulls · DammianMiller/universal-agent-protocol · @DammianMiller](https://github.com/DammianMiller/universal-agent-protocol/pull/887)
> listed only the live Flash-Next alias — the Qwen3.8 **27B** family (the registry's `qwen3.8-27b`: the llama.cpp/yskn/HyperQwen-class arms) had no line, even as the fleet's 27B
- 2026-11-15T11:44:00.590Z · [GitHub search · Alibaba · pulls · Helicone/helicone · @acheamponge](https://github.com/Helicone/helicone/pull/5777)
> (GLM 5.3, DeepSeek V4.1 Flash, gpt-oss-120b, Gemma 4, Qwen3.8, Nemotron 3.5) at `https://api.inference.crusoecloud.com/v1`. Crusoe is a supported provider in LiteLLM, Pydantic AI, Pipecat, aisuite, the
- 2026-11-15T11:44:00.590Z · [GitHub search · Alibaba · pulls · Kreijstal/pi-managed-workflow · @renovate[bot]](https://github.com/Kreijstal/pi-managed-workflow/pull/3)
> using catalog metadata, with verified DeepSeek V4 and Qwen3.8 fallbacks and removal of redundant GLM 5.2 and Kimi K3 effort aliases ([#​9323](https://redirect.github.com/earendil-works/pi/issues/9323)).
- 2026-11-15T11:44:00.590Z · [GitHub search · Alibaba · pulls · cgfixit/CG-agent-harness · @cgfixit](https://github.com/cgfixit/CG-agent-harness/pull/887)
> and the configured local model (`models.local_llm.model`, verified with `qwen3.8:27b-mlx-cg` on a 32K window) drives a real Chrome through a Playwright sidecar on only the named
- 2026-11-15T11:44:00.590Z · [GitHub search · Alibaba · pulls · fsdatalab/quail · @shreyashankar](https://github.com/fsdatalab/quail/pull/304)
> Tokenize Qwen3.5 and Qwen3.8 models: tokenizers 1.0.0-rc.4 with its regex backend
- 2026-11-15T12:04:06.232Z · [GitHub search · Alibaba · pulls · BerdalYe/Foundry · @BerdalYe](https://github.com/BerdalYe/Foundry/pull/1)
> - **Picker:** GPT-OSS 120B (default), GPT-OSS 20B and Qwen3.8 27B. Qwen is labelled as a preview model, since Groq can withdraw preview models at short
- 2026-11-15T12:04:06.232Z · [GitHub search · Alibaba · pulls · guiinow/Jev-LLM-callibration · @luisaporf](https://github.com/guiinow/Jev-LLM-callibration/pull/3)
> model (Qwen2.5-0.5B-Instruct); not yet run on Gemma-4 or Qwen3.8. Validate with `check-benchmark` in C1 first.
- 2026-11-15T12:04:06.232Z · [GitHub search · Alibaba · pulls · wyrd-company/ahp-pi-agent · @renovate[bot]](https://github.com/wyrd-company/ahp-pi-agent/pull/4)
> using catalog metadata, with verified DeepSeek V4 and Qwen3.8 fallbacks and removal of redundant GLM 5.2 and Kimi K3 effort aliases ([#​9323](https://redirect.github.com/earendil-works/pi/issues/9323)).
- 2026-11-15T12:22:20.516Z · [GitHub search · Alibaba · pulls · Magnus-Gille/gille-inference · @Magnus-Gille](https://github.com/Magnus-Gille/gille-inference/pull/520)
> The current Qwen3.8 runtime pin predates any Qwen 4 architecture upstream, so release day needs a newer runtime bundle anyway. Writing down a starting point
- 2026-11-15T12:22:20.516Z · [GitHub search · Alibaba · pulls · anomalyco/models.dev · @tonydavis629](https://github.com/anomalyco/models.dev/pull/11270)
> vs 1,000,000), Llama 3.3 70B (131,072 vs 128,000), Qwen3.8 27B
- 2026-11-15T12:22:20.516Z · [GitHub search · Alibaba · pulls · anomalyco/models.dev · @kingsleydon](https://github.com/anomalyco/models.dev/pull/11447)
- 2026-11-15T12:22:20.516Z · [GitHub search · Alibaba · pulls · anomalyco/models.dev · @whiteworthy](https://github.com/anomalyco/models.dev/pull/13185)
> for the same upstream (so Kimi keeps BMP, Qwen3.8 Max keeps BMP/TIFF, Ember-1 inherits the lab list, and HEIC is dropped where it failed in
- 2026-11-15T12:22:20.516Z · [GitHub search · Alibaba · pulls · anomalyco/models.dev · @codemama-agent](https://github.com/anomalyco/models.dev/pull/13359)
- 2026-11-15T12:22:20.516Z · [GitHub search · Alibaba · pulls · hyukudan/strix-halo-engine-lab · @hyukudan](https://github.com/hyukudan/strix-halo-engine-lab/pull/608)
> - docs/models/qwen3.8/README.md / README.es.md: the Weights line links it.
- 2026-11-15T12:22:20.516Z · [GitHub search · Alibaba · pulls · jpenilla/pi-cloudflare-ai-gateway-native · @renovate[bot]](https://github.com/jpenilla/pi-cloudflare-ai-gateway-native/pull/10)
> using catalog metadata, with verified DeepSeek V4 and Qwen3.8 fallbacks and removal of redundant GLM 5.2 and Kimi K3 effort aliases ([#​9323](https://redirect.github.com/earendil-works/pi/issues/9323)).
- 2026-11-15T12:22:20.516Z · [GitHub search · Alibaba · pulls · metorial/metorial-platform · @herber](https://github.com/metorial/metorial-platform/pull/1229)
- 2026-11-15T12:22:20.516Z · [GitHub search · Alibaba · pulls · metorial/metorial-platform · @herber](https://github.com/metorial/metorial-platform/pull/1231)
> | `adaption/qwen3.8-27b` | link → `alibaba/qwen3.8-27b` | Offering is exactly Qwen3.8 27B (text+image input, 262K context match); Adaption's odd cheap-input/expensive-output split is vendor pricing, not
- 2026-11-15T12:22:20.516Z · [GitHub search · Alibaba · pulls · pydantic/pydantic-ai · @pydanty[bot]](https://github.com/pydantic/pydantic-ai/pull/12667)
- 2026-11-15T12:22:44.052Z · [GitHub search · Alibaba · commits · hyukudan/strix-halo-engine-lab · @hyukudan](https://github.com/hyukudan/strix-halo-engine-lab/commit/db532048a2aa94cde2572352388e8f40332b58d1)
> docs/serving*.md, docs/models/{qwen3.8,deepseek-v4.1,glm-5.3,minimax-m3.1}/README*.md
- 2026-11-15T12:22:44.052Z · [GitHub search · Alibaba · commits · sprout-foundry/sprout · @alantheprice](https://github.com/sprout-foundry/sprout/commit/f825cce63ad04a318b1d9797c28431dd2ebe125d)
> feat(agent_providers): add qwen3.8 reasoning fallback and effort levels
- 2026-11-15T12:39:57.670Z · [GitHub search · Alibaba · pulls · ddalcu/mlx-serve · @dmumber](https://github.com/ddalcu/mlx-serve/pull/981)
> E3-ED), plus a bare F0/EF, because a masked Qwen3.8 otherwise spelled plane-2 Han from a bare F0; no emoji or VS16 needs those tokens in
- 2026-11-15T12:39:57.670Z · [GitHub search · Alibaba · pulls · jakeryderv/pi-agent-bridge · @dependabot[bot]](https://github.com/jakeryderv/pi-agent-bridge/pull/6)
> inherited Qwen Token Plan Individual catalog to include Qwen3.8 Flash (<a href="https://redirect.github.com/earendil-works/pi/issues/9021">#9021</a>).</li>
- 2026-11-15T12:39:57.670Z · [GitHub search · Alibaba · pulls · trymirai/uzu · @xianml](https://github.com/trymirai/uzu/pull/1065)
> up to `>` in the Qwen3.5/3.6 XML parsers; Qwen3.8
- 2026-11-15T12:40:17.242Z · [GitHub search · Alibaba · commits · anomalyco/models.dev · @unrestricted-dev](https://github.com/anomalyco/models.dev/commit/a1b1e6baa40e78fd3c74c1f781f54feb3f18f290)
> * fix: align reasoning levels with Qwen3.8 27B peers
- 2026-11-15T12:40:17.242Z · [GitHub search · Alibaba · commits · anomalyco/models.dev · @mahir-lyceum](https://github.com/anomalyco/models.dev/commit/af92dfd47834af9346617641eb5512f1600c9e93)
> the replacement models (GLM-5.3 and Qwen3.8 27B), so they should not
- 2026-11-15T12:40:17.242Z · [GitHub search · Alibaba · commits · cogine-ai/modelspage · @unrestricted-dev](https://github.com/cogine-ai/modelspage/commit/a1b1e6baa40e78fd3c74c1f781f54feb3f18f290)
> * fix: align reasoning levels with Qwen3.8 27B peers
- 2026-11-15T12:40:17.242Z · [GitHub search · Alibaba · commits · cogine-ai/modelspage · @mahir-lyceum](https://github.com/cogine-ai/modelspage/commit/af92dfd47834af9346617641eb5512f1600c9e93)
> the replacement models (GLM-5.3 and Qwen3.8 27B), so they should not
- 2026-11-15T12:40:17.242Z · [GitHub search · Alibaba · commits · hyukudan/strix-halo-engine-lab · @hyukudan](https://github.com/hyukudan/strix-halo-engine-lab/commit/acefcf459742a81794ba390bd2173f36852d3941)
> docs/serving*.md, docs/models/{qwen3.8,deepseek-v4.1,glm-5.3,minimax-m3.1}/README*.md
- 2026-11-15T12:40:17.242Z · [GitHub search · Alibaba · commits · hyukudan/strix-halo-engine-lab · @hyukudan](https://github.com/hyukudan/strix-halo-engine-lab/commit/fd9cd3f5dba59350151e0bcdd1fd6c69f3c23d29)
> docs/serving*.md, docs/models/{qwen3.8,deepseek-v4.1,glm-5.3,minimax-m3.1}/README*.md
- 2026-11-15T12:54:58.342Z · [GitHub search · Alibaba · pulls · CommunityServe/plugins · @davidtai](https://github.com/CommunityServe/plugins/pull/49)
> Its NLL change is in ordinary tokens. On Qwen3.8,
- 2026-11-15T12:54:58.342Z · [GitHub search · Alibaba · pulls · talstilkol/lumen-md · @talstilkol](https://github.com/talstilkol/lumen-md/pull/590)
- 2026-11-15T12:54:58.342Z · [GitHub search · Alibaba · pulls · willchan/bamboo · @willchan](https://github.com/willchan/bamboo/pull/31)
> Qwen 3.8: qwen3.8:27b is OpenClaw's reply model
- 2026-11-15T13:10:14.954Z · [GitHub search · Alibaba · pulls · PreventiveMeasures/libraries · @ChristopherTuring](https://github.com/PreventiveMeasures/libraries/pull/459)
> - No-think table and provider wire tests: Qwen3.8 Flash joins the models sent `reasoning: {enabled: false}`. Large 4 moves from that group to the "sends
- 2026-11-15T13:10:14.954Z · [GitHub search · Alibaba · pulls · Quarkgluonmixture/quarkspace · @github-actions[bot]](https://github.com/Quarkgluonmixture/quarkspace/pull/130)
- 2026-11-15T13:10:14.954Z · [GitHub search · Alibaba · pulls · behroozazarkhalili/GRPO-Finetuning-Unsloth · @renovate[bot]](https://github.com/behroozazarkhalili/GRPO-Finetuning-Unsloth/pull/9)
- 2026-11-15T13:10:14.954Z · [GitHub search · Alibaba · pulls · dev400-jd/opencode-ollama-agents · @dev400-jd](https://github.com/dev400-jd/opencode-ollama-agents/pull/1)
> - performance.md: record the qwen3.8:27b trial on 24 GB (Metal out-of-memory on the first coordinator prompt, 4096 default context of the Ollama app)
- 2026-11-15T13:10:14.954Z · [GitHub search · Alibaba · pulls · hypertask-ai/hypertask · @hypertask-runners[bot]](https://github.com/hypertask-ai/hypertask/pull/3503)
> classes, after the first three (Kimi K3.1 Pro, Qwen3.8 Max, Qwen3.8 Max Prime) shipped in https://github.com/hypertask-ai/hypertask/pull/3476.
- 2026-11-15T13:10:14.954Z · [GitHub search · Alibaba · pulls · hyukudan/strix-halo-engine-lab · @hyukudan](https://github.com/hyukudan/strix-halo-engine-lab/pull/474)
> Docs: docs/engine/speculative/mtp-native-cli.md, AGENTS.md, README.md, docs/models/qwen3.8/README.md
- 2026-11-15T13:10:14.954Z · [GitHub search · Alibaba · pulls · hyukudan/strix-halo-engine-lab · @hyukudan](https://github.com/hyukudan/strix-halo-engine-lab/pull/480)
> Docs: docs/models/qwen3.8/persistence-kernels.md
- 2026-11-15T13:10:14.954Z · [GitHub search · Alibaba · pulls · hyukudan/strix-halo-engine-lab · @hyukudan](https://github.com/hyukudan/strix-halo-engine-lab/pull/527)
> Docs: docs/optimizations.md, docs/models/qwen3.8/README.md, docs/models/qwen3.8/README.es.md, docs/engine/kernels/gdn-fp16-chunk.md
- 2026-11-15T13:10:14.954Z · [GitHub search · Alibaba · pulls · incoai/splash · @Thomas-Zenkel](https://github.com/incoai/splash/pull/619)
> `StopIteration`. DeepSeek reports `low`, `high` (default) and `max`; Qwen3.8's reports are unchanged.
- 2026-11-15T13:10:14.954Z · [GitHub search · Alibaba · pulls · zhongkaifu/TensorSharp · @zhongkaifu](https://github.com/zhongkaifu/TensorSharp/pull/371)
> - Qwen3.8's delta-net output norm (a sigmoid gate) runs on the fused gated-norm kernel, which took silu only (a DEFAULT CHANGE): verify -0.1-0.2 ms.
- 2026-11-15T13:10:37.034Z · [GitHub search · Alibaba · commits · kwokkc7217-netizen/hk-daily-places · @unknown](https://github.com/kwokkc7217-netizen/hk-daily-places/commit/69c6e7f518340d413e407088d4e00eaece7956bf)
> (qwen/qwen3.8-27b, Qwen3.8 27B — verified free-tier model: 30 RPM,
- 2026-11-15T13:10:37.034Z · [GitHub search · Alibaba · commits · willchan/bamboo · @willchan](https://github.com/willchan/bamboo/commit/63bb6b6bc5a0ede92ec572c167aa453dcacdf364)
> Qwen 3.8: qwen3.8:27b is OpenClaw's reply model (#31)
- 2026-11-15T13:25:14.480Z · [GitHub search · Alibaba · pulls · CherryHQ/cherry-studio · @kangfenmao](https://github.com/CherryHQ/cherry-studio/pull/22550)
> - Regression — Electron with Ollama 0.34.3 / `qwen3.8:27b`: native model refresh, preserved custom context window, all five UI-to-wire selections, real `OK` reply with thinking
- 2026-11-15T13:25:14.480Z · [GitHub search · Alibaba · pulls · DammianMiller/universal-agent-protocol · @DammianMiller](https://github.com/DammianMiller/universal-agent-protocol/pull/883)
> > Custom model "Qwen3.8 Flash-Next (UAP local)" does not map to a built-in model, so it does not inherit model-specific prompts, tools, reasoning settings, or
- 2026-11-15T13:25:14.480Z · [GitHub search · Alibaba · pulls · DammianMiller/universal-agent-protocol · @DammianMiller](https://github.com/DammianMiller/universal-agent-protocol/pull/884)
> > Custom model "Qwen3.8 Flash-Next (UAP local)" does not map to a built-in model, so it does not inherit model-specific prompts, tools, reasoning settings, or
- 2026-11-15T13:25:14.480Z · [GitHub search · Alibaba · pulls · ILIV007/IVAI-bot · @ILIV007](https://github.com/ILIV007/IVAI-bot/pull/45)
> feat: free model catalog refresh, comments move to Qwen3.8 27B (v3.14.0)
- 2026-11-15T13:25:14.480Z · [GitHub search · Alibaba · pulls · austery/thought-foundry-content · @austery](https://github.com/austery/thought-foundry-content/pull/11)
> Flash via Antigravity first (89 notes), then local `qwen3.8:27b-mlx` for the notes it failed (21 notes), plus 9 podcast articles from an earlier Qwen pass.
- 2026-11-15T13:25:14.480Z · [GitHub search · Alibaba · pulls · hyukudan/strix-halo-engine-lab · @hyukudan](https://github.com/hyukudan/strix-halo-engine-lab/pull/557)
> Docs: docs/engine/kernels/moe-route-prune.md, docs/models/qwen3.8/README.md, docs/models/qwen3.8/README.es.md
- 2026-11-15T13:25:14.480Z · [GitHub search · Alibaba · pulls · juw12/projects · @juw12](https://github.com/juw12/projects/pull/72)
- 2026-11-15T13:25:14.480Z · [GitHub search · Alibaba · pulls · snorkel-marlin-repos/ray-project_ray_pr_56005_88d9466a-0611-46d8-b978-1b015005f3d2 · @dependabot[bot]](https://github.com/snorkel-marlin-repos/ray-project_ray_pr_56005_88d9466a-0611-46d8-b978-1b015005f3d2/pull/61)
- 2026-11-15T13:25:14.480Z · [GitHub search · Alibaba · pulls · snorkel-marlin-repos/ray-project_ray_pr_57600_7e02269e-6e19-4ee8-a721-1e7e6ed0e61d · @dependabot[bot]](https://github.com/snorkel-marlin-repos/ray-project_ray_pr_57600_7e02269e-6e19-4ee8-a721-1e7e6ed0e61d/pull/64)
- 2026-11-15T13:41:05.054Z · [GitHub search · Alibaba · pulls · HaroldLui/COMP7611-Group-Project · @HaroldLui](https://github.com/HaroldLui/COMP7611-Group-Project/pull/12)
> Add cross-model comparison and report section (DeepSeek, GLM-5.3, Qwen3.8)
- 2026-11-15T13:41:05.054Z · [GitHub search · Alibaba · pulls · RBLN-SW/vllm-rbln · @rebel-seinpark](https://github.com/RBLN-SW/vllm-rbln/pull/1431)
- 2026-11-15T13:41:05.054Z · [GitHub search · Alibaba · pulls · Trollz1004/ANTIGRAVITY · @Trollz1004](https://github.com/Trollz1004/ANTIGRAVITY/pull/402)
- 2026-11-15T13:41:05.054Z · [GitHub search · Alibaba · pulls · canonical/ollama-sdk · @renovate[bot]](https://github.com/canonical/ollama-sdk/pull/57)
- 2026-11-15T13:41:05.054Z · [GitHub search · Alibaba · pulls · hypertask-ai/hypertask · @hypertask-runners[bot]](https://github.com/hypertask-ai/hypertask/pull/3476)
> HTPR-8207 [IMPROVE] Add Kimi K3.1 Pro and Qwen3.8 Max to the model pickers
- 2026-11-15T13:41:05.054Z · [GitHub search · Alibaba · pulls · lobehub/lobehub · @Dhirenderchoudhary](https://github.com/lobehub/lobehub/pull/23008)
> Pro, DeepSeek V4 Flash, GLM-5.2, Kimi K2.7 Code, Qwen3.8 Max and MiniMax M3. Abilities (tool calls, reasoning, vision) and prices were checked against the live
- 2026-11-15T13:41:24.348Z · [GitHub search · Alibaba · commits · DammianMiller/universal-agent-protocol · @unknown](https://github.com/DammianMiller/universal-agent-protocol/commit/d7819aadc4d2139cc7f1b8e5fdd1d703de1e6d74)
> The warning: custom model 'Qwen3.8 Flash-Next (UAP local)' does not map to
- 2026-11-15T13:56:17.787Z · [GitHub search · Alibaba · pulls · lkl03/promptea · @lkl03](https://github.com/lkl03/promptea/pull/47)
> - Qwen3.8 Max / 3.7 Plus / 3.8 Flash (Alibaba Cloud Model Studio).
- 2026-11-15T13:56:17.787Z · [GitHub search · Alibaba · pulls · thelaggingway/resource-library · @thelaggingway](https://github.com/thelaggingway/resource-library/pull/53)
> - Removed from the published library (11): Qwen3.6-27B-MTP-GGUF, Qwen3.8-27B-GGUF, Qwen3.8 open weights announcement, Hy4-preview-FP8, GLM-5.3-Flash-DFlash2, MiniCPM5-2B-PCD, LFM2.5-2.6B-RLCD, Qwen-2.5-1B-RLCD, kimi-k3-mlx, GLiNER2.5-Decide, Unlimited OCR.
- 2026-11-15T13:56:17.787Z · [GitHub search · Alibaba · pulls · vjmichael/Lu-AI-GUI · @vjmichael](https://github.com/vjmichael/Lu-AI-GUI/pull/226)
> - Physical interactive owner Windows/Radeon Qwen3.8, Vulkan VRAM/TFFB TTFT p50/p95, and actual local installed MMProj; hosted CPU small models do not substitute.
- 2026-11-15T13:56:17.787Z · [GitHub search · Alibaba · pulls · vjmichael/Lu-AI-GUI · @vjmichael](https://github.com/vjmichael/Lu-AI-GUI/pull/228)
> owner authorization for a staged bottom-up integration. Physical Radeon/Qwen3.8 and Browser `not-packaged` remain separate release gates.
- 2026-11-15T13:57:11.022Z · [GitHub search · Alibaba · commits · Nitjsefnie/ai-researcher · @github-actions[bot]](https://github.com/Nitjsefnie/ai-researcher/commit/77ee0cdd64b90b5a45d35155e167cadcdc89c125)
- 2026-11-15T13:57:11.022Z · [GitHub search · Alibaba · commits · Trollz1004/ANTIGRAVITY · @Trollz1004](https://github.com/Trollz1004/ANTIGRAVITY/commit/f5e9aebda2acdaab729401d4c4391656f93399a6)
- 2026-11-15T13:57:11.022Z · [GitHub search · Alibaba · commits · jwkim04/tesseract-npu · @jwkim0410](https://github.com/jwkim04/tesseract-npu/commit/12fbc02f6d3ec34ded66f2c4dca379df1a1ad874)
> 1: Gemma 4 26B-A4B 17.54 -> 17.67 tokens/s, Qwen3.8 27B 4.49 ->

## پیوندهای شواهد

- [Alex Getman](https://alexgetman.com/184/alibaba-open-sourced-qwen3-8/)
- [Alex Getman](https://alexgetman.com/196/qwen-3-8-27b-beat-gpt-5-6-terra/)
- [editorial](https://alexgetman.com/356/qwen3-8-flash-next-drops-today/)
- [editorial](https://alexgetman.com/357/qwen3-8-flash-next-is-out/)
- [editorial](https://alexgetman.com/428/qwen3-8-omni-flash-is-out/)
- [editorial](https://alexgetman.com/86/alibaba-just-teased-qwen3-8-with-2-4t-parameters/)
- [GitHub search · Alibaba · pulls · 0xburden/modelship · @0xburden](https://github.com/0xburden/modelship/pull/8)
- [GitHub search · Alibaba · commits · Azure/azureml-assets · @hanbitmyths](https://github.com/Azure/azureml-assets/commit/229f9a3bd592035925db8d0a49fd65f8b5c43998)
- [GitHub search · Alibaba · pulls · Azure/azureml-assets · @hanbitmyths](https://github.com/Azure/azureml-assets/pull/5452)
- [GitHub search · Alibaba · pulls · BerdalYe/Foundry · @BerdalYe](https://github.com/BerdalYe/Foundry/pull/1)
- [GitHub search · Alibaba · pulls · BuQQzz/SHIELD2.0 · @BuQQzz](https://github.com/BuQQzz/SHIELD2.0/pull/56)
- [GitHub search · Alibaba · pulls · CherryHQ/cherry-studio · @kangfenmao](https://github.com/CherryHQ/cherry-studio/pull/22550)
- [GitHub search · Alibaba · pulls · CommunityServe/plugins · @davidtai](https://github.com/CommunityServe/plugins/pull/49)
- [GitHub search · Alibaba · commits · DammianMiller/universal-agent-protocol · @unknown](https://github.com/DammianMiller/universal-agent-protocol/commit/d7819aadc4d2139cc7f1b8e5fdd1d703de1e6d74)
- [GitHub search · Alibaba · pulls · DammianMiller/universal-agent-protocol · @DammianMiller](https://github.com/DammianMiller/universal-agent-protocol/pull/883)
- [GitHub search · Alibaba · pulls · DammianMiller/universal-agent-protocol · @DammianMiller](https://github.com/DammianMiller/universal-agent-protocol/pull/884)
- [GitHub search · Alibaba · pulls · DammianMiller/universal-agent-protocol · @DammianMiller](https://github.com/DammianMiller/universal-agent-protocol/pull/887)
- [GitHub search · Alibaba · pulls · Finkregh/stepstone-hierarchy · @renovate[bot]](https://github.com/Finkregh/stepstone-hierarchy/pull/11)
- [GitHub search · Alibaba · pulls · FlashML-org/FreeToken · @zihaomu](https://github.com/FlashML-org/FreeToken/pull/897)
- [GitHub search · Alibaba · commits · Hallo-ich-bin-PeppaPig/Singularity · @Hallo-ich-bin-PeppaPig](https://github.com/Hallo-ich-bin-PeppaPig/Singularity/commit/b33219c6ead9582f7e03467b2d6885718bbe16cc)
- [GitHub search · Alibaba · pulls · HaroldLui/COMP7611-Group-Project · @HaroldLui](https://github.com/HaroldLui/COMP7611-Group-Project/pull/12)
- [GitHub search · Alibaba · pulls · Helicone/helicone · @acheamponge](https://github.com/Helicone/helicone/pull/5777)
- [GitHub search · Alibaba · pulls · IBM/Evoflux · @renovate[bot]](https://github.com/IBM/Evoflux/pull/11)
- [GitHub search · Alibaba · pulls · ILIV007/IVAI-bot · @ILIV007](https://github.com/ILIV007/IVAI-bot/pull/45)
- [GitHub search · Alibaba · pulls · Kreijstal/pi-managed-workflow · @renovate[bot]](https://github.com/Kreijstal/pi-managed-workflow/pull/3)
- [GitHub search · Alibaba · pulls · Magnus-Gille/gille-inference · @Magnus-Gille](https://github.com/Magnus-Gille/gille-inference/pull/520)
- [GitHub search · Alibaba · pulls · NVIDIA/hyperflare-inference · @Raydius](https://github.com/NVIDIA/hyperflare-inference/pull/212)
- [GitHub search · Alibaba · commits · Nitjsefnie/ai-researcher · @github-actions[bot]](https://github.com/Nitjsefnie/ai-researcher/commit/77ee0cdd64b90b5a45d35155e167cadcdc89c125)
- [GitHub search · Alibaba · pulls · PreventiveMeasures/libraries · @ChristopherTuring](https://github.com/PreventiveMeasures/libraries/pull/459)
- [GitHub search · Alibaba · commits · QuantumKuba/Diffactly · @QuantumKuba](https://github.com/QuantumKuba/Diffactly/commit/77529540c23a8e7419a0147263f52ad0078ae3df)
- [GitHub search · Alibaba · pulls · Quarkgluonmixture/quarkspace · @github-actions[bot]](https://github.com/Quarkgluonmixture/quarkspace/pull/130)
- [GitHub · QwenLM/qwen-code · PR](https://github.com/QwenLM/qwen-code/pull/15184)
- [GitHub search · Alibaba · pulls · RBLN-SW/vllm-rbln · @rebel-seinpark](https://github.com/RBLN-SW/vllm-rbln/pull/1431)
- [GitHub search · Alibaba · pulls · SceneWorks/SceneWorks · @michaeltrefry](https://github.com/SceneWorks/SceneWorks/pull/3383)
- [GitHub search · Alibaba · commits · Trollz1004/ANTIGRAVITY · @Trollz1004](https://github.com/Trollz1004/ANTIGRAVITY/commit/f5e9aebda2acdaab729401d4c4391656f93399a6)
- [GitHub search · Alibaba · pulls · Trollz1004/ANTIGRAVITY · @Trollz1004](https://github.com/Trollz1004/ANTIGRAVITY/pull/402)
- [GitHub search · Alibaba · commits · aabhay007/Personal-AI-Core · @aabhay007](https://github.com/aabhay007/Personal-AI-Core/commit/54e756490e80be233ca0314f9fed50baad560413)
- [GitHub search · Alibaba · commits · agentgateway/agentgateway · @github-actions[bot]](https://github.com/agentgateway/agentgateway/commit/b7f833ec371abdb5a58fe64c9a7409a51cd1d11c)
- [GitHub search · Alibaba · pulls · alondigitized/ai-files · @alondigitized](https://github.com/alondigitized/ai-files/pull/104)
- [GitHub search · Alibaba · commits · anomalyco/models.dev · @unrestricted-dev](https://github.com/anomalyco/models.dev/commit/a1b1e6baa40e78fd3c74c1f781f54feb3f18f290)
- [GitHub search · Alibaba · commits · anomalyco/models.dev · @mahir-lyceum](https://github.com/anomalyco/models.dev/commit/af92dfd47834af9346617641eb5512f1600c9e93)
- [GitHub search · Alibaba · pulls · anomalyco/models.dev · @tonydavis629](https://github.com/anomalyco/models.dev/pull/11270)
- [GitHub search · Alibaba · pulls · anomalyco/models.dev · @kingsleydon](https://github.com/anomalyco/models.dev/pull/11447)
- [GitHub search · Alibaba · pulls · anomalyco/models.dev · @whiteworthy](https://github.com/anomalyco/models.dev/pull/13185)
- [GitHub search · Alibaba · pulls · anomalyco/models.dev · @codemama-agent](https://github.com/anomalyco/models.dev/pull/13359)
- [GitHub search · Alibaba · pulls · austery/thought-foundry-content · @austery](https://github.com/austery/thought-foundry-content/pull/11)
- [GitHub search · Alibaba · pulls · behroozazarkhalili/GRPO-Finetuning-Unsloth · @renovate[bot]](https://github.com/behroozazarkhalili/GRPO-Finetuning-Unsloth/pull/9)
- [GitHub search · Alibaba · pulls · canonical/ollama-sdk · @renovate[bot]](https://github.com/canonical/ollama-sdk/pull/57)
- [GitHub search · Alibaba · pulls · celve/miles · @celve](https://github.com/celve/miles/pull/46)
- [GitHub search · Alibaba · pulls · cgfixit/CG-agent-harness · @cgfixit](https://github.com/cgfixit/CG-agent-harness/pull/887)
- [GitHub search · Alibaba · commits · cogine-ai/modelspage · @unrestricted-dev](https://github.com/cogine-ai/modelspage/commit/a1b1e6baa40e78fd3c74c1f781f54feb3f18f290)
- [GitHub search · Alibaba · commits · cogine-ai/modelspage · @mahir-lyceum](https://github.com/cogine-ai/modelspage/commit/af92dfd47834af9346617641eb5512f1600c9e93)
- [GitHub search · Alibaba · pulls · copse-dev/agent-pane · @jonathanKingston](https://github.com/copse-dev/agent-pane/pull/4294)
- [GitHub search · Alibaba · pulls · ddalcu/mlx-serve · @dmumber](https://github.com/ddalcu/mlx-serve/pull/981)
- [GitHub search · Alibaba · pulls · dev400-jd/opencode-ollama-agents · @dev400-jd](https://github.com/dev400-jd/opencode-ollama-agents/pull/1)
- [GitHub search · Alibaba · pulls · engeldlgado/toshllm · @andruwa13](https://github.com/engeldlgado/toshllm/pull/165)
- [GitHub search · Alibaba · commits · fdietze/pi-infinite-context · @fdietze](https://github.com/fdietze/pi-infinite-context/commit/af207012a9c5522c75abcf01352ef15b166e983c)
- [GitHub search · Alibaba · commits · finereli/pyramid-mcp · @finereli](https://github.com/finereli/pyramid-mcp/commit/279f60c731b0ee6d5fe2b68bb2cfe24b97358c64)
- [GitHub search · Alibaba · pulls · fsdatalab/quail · @shreyashankar](https://github.com/fsdatalab/quail/pull/304)
- [GitHub search · Alibaba · pulls · guiinow/Jev-LLM-callibration · @luisaporf](https://github.com/guiinow/Jev-LLM-callibration/pull/3)
- [GitHub search · Alibaba · pulls · hypertask-ai/hypertask · @hypertask-runners[bot]](https://github.com/hypertask-ai/hypertask/pull/3476)
- [GitHub search · Alibaba · pulls · hypertask-ai/hypertask · @hypertask-runners[bot]](https://github.com/hypertask-ai/hypertask/pull/3503)
- [GitHub search · Alibaba · commits · hyukudan/strix-halo-engine-lab · @hyukudan](https://github.com/hyukudan/strix-halo-engine-lab/commit/acefcf459742a81794ba390bd2173f36852d3941)
- [GitHub search · Alibaba · commits · hyukudan/strix-halo-engine-lab · @hyukudan](https://github.com/hyukudan/strix-halo-engine-lab/commit/db532048a2aa94cde2572352388e8f40332b58d1)
- [GitHub search · Alibaba · commits · hyukudan/strix-halo-engine-lab · @hyukudan](https://github.com/hyukudan/strix-halo-engine-lab/commit/fd9cd3f5dba59350151e0bcdd1fd6c69f3c23d29)
- [GitHub search · Alibaba · pulls · hyukudan/strix-halo-engine-lab · @hyukudan](https://github.com/hyukudan/strix-halo-engine-lab/pull/474)
- [GitHub search · Alibaba · pulls · hyukudan/strix-halo-engine-lab · @hyukudan](https://github.com/hyukudan/strix-halo-engine-lab/pull/480)
- [GitHub search · Alibaba · pulls · hyukudan/strix-halo-engine-lab · @hyukudan](https://github.com/hyukudan/strix-halo-engine-lab/pull/527)
- [GitHub search · Alibaba · pulls · hyukudan/strix-halo-engine-lab · @hyukudan](https://github.com/hyukudan/strix-halo-engine-lab/pull/557)
- [GitHub search · Alibaba · pulls · hyukudan/strix-halo-engine-lab · @hyukudan](https://github.com/hyukudan/strix-halo-engine-lab/pull/608)
- [GitHub search · Alibaba · pulls · incoai/splash · @Thomas-Zenkel](https://github.com/incoai/splash/pull/619)
- [GitHub search · Alibaba · pulls · jakeryderv/pi-agent-bridge · @dependabot[bot]](https://github.com/jakeryderv/pi-agent-bridge/pull/6)
- [GitHub search · Alibaba · pulls · jpenilla/pi-cloudflare-ai-gateway-native · @renovate[bot]](https://github.com/jpenilla/pi-cloudflare-ai-gateway-native/pull/10)
- [GitHub search · Alibaba · pulls · juw12/projects · @juw12](https://github.com/juw12/projects/pull/72)
- [GitHub search · Alibaba · commits · jwkim04/tesseract-npu · @jwkim0410](https://github.com/jwkim04/tesseract-npu/commit/12fbc02f6d3ec34ded66f2c4dca379df1a1ad874)
- [GitHub search · Alibaba · commits · kwokkc7217-netizen/hk-daily-places · @unknown](https://github.com/kwokkc7217-netizen/hk-daily-places/commit/69c6e7f518340d413e407088d4e00eaece7956bf)
- [GitHub search · Alibaba · pulls · lkl03/promptea · @lkl03](https://github.com/lkl03/promptea/pull/47)
- [GitHub search · Alibaba · pulls · lobehub/lobehub · @Dhirenderchoudhary](https://github.com/lobehub/lobehub/pull/23008)
- [GitHub search · Alibaba · commits · logicplanes/kaeso · @dvnold](https://github.com/logicplanes/kaeso/commit/3d742a5cd4e6b39f902b3dec668377e394559c74)
- [GitHub search · Alibaba · pulls · logicplanes/kaeso · @dvnold](https://github.com/logicplanes/kaeso/pull/1109)
- [GitHub search · Alibaba · pulls · metorial/metorial-platform · @herber](https://github.com/metorial/metorial-platform/pull/1229)
- [GitHub search · Alibaba · pulls · metorial/metorial-platform · @herber](https://github.com/metorial/metorial-platform/pull/1231)
- [GitHub search · Alibaba · pulls · michsindlinger/specwright · @michsindlinger](https://github.com/michsindlinger/specwright/pull/125)
- [GitHub search · Alibaba · pulls · nearai/cvm-compose-files · @PierreLeGuen](https://github.com/nearai/cvm-compose-files/pull/488)
- [GitHub search · Alibaba · commits · onprem-ai/deployment-catalog · @tomas-polach](https://github.com/onprem-ai/deployment-catalog/commit/13545a9aa19112ab1251fe153caa0cf872afddc1)
- [GitHub search · Alibaba · pulls · orioli/IM-LLM · @Mihawii](https://github.com/orioli/IM-LLM/pull/1)
- [GitHub search · Alibaba · pulls · pydantic/pydantic-ai · @pydanty[bot]](https://github.com/pydantic/pydantic-ai/pull/12667)
- [GitHub search · Alibaba · pulls · radixark/miles · @celve](https://github.com/radixark/miles/pull/4857)
- [GitHub search · Alibaba · commits · saumen/llama-server-launcher · @saumen](https://github.com/saumen/llama-server-launcher/commit/3406f69992a621de1850b391896294d569703f20)
- [GitHub search · Alibaba · pulls · siddsachar/row-bot · @siddsachar](https://github.com/siddsachar/row-bot/pull/898)
- [GitHub search · Alibaba · pulls · slimsami/strycast · @slimsami](https://github.com/slimsami/strycast/pull/71)
- [GitHub search · Alibaba · pulls · snorkel-marlin-repos/ray-project_ray_pr_56005_88d9466a-0611-46d8-b978-1b015005f3d2 · @dependabot[bot]](https://github.com/snorkel-marlin-repos/ray-project_ray_pr_56005_88d9466a-0611-46d8-b978-1b015005f3d2/pull/61)
- [GitHub search · Alibaba · pulls · snorkel-marlin-repos/ray-project_ray_pr_57600_7e02269e-6e19-4ee8-a721-1e7e6ed0e61d · @dependabot[bot]](https://github.com/snorkel-marlin-repos/ray-project_ray_pr_57600_7e02269e-6e19-4ee8-a721-1e7e6ed0e61d/pull/64)
- [GitHub search · Alibaba · commits · sprout-foundry/sprout · @alantheprice](https://github.com/sprout-foundry/sprout/commit/f825cce63ad04a318b1d9797c28431dd2ebe125d)
- [GitHub search · Alibaba · pulls · talstilkol/lumen-md · @talstilkol](https://github.com/talstilkol/lumen-md/pull/590)
- [GitHub search · Alibaba · pulls · thelaggingway/resource-library · @thelaggingway](https://github.com/thelaggingway/resource-library/pull/53)
- [GitHub search · Alibaba · pulls · trymirai/uzu · @xianml](https://github.com/trymirai/uzu/pull/1065)
- [GitHub search · Alibaba · pulls · vjmichael/Lu-AI-GUI · @vjmichael](https://github.com/vjmichael/Lu-AI-GUI/pull/226)
- [GitHub search · Alibaba · pulls · vjmichael/Lu-AI-GUI · @vjmichael](https://github.com/vjmichael/Lu-AI-GUI/pull/228)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/2629)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/2895)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3232)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3233)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3234)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3235)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3236)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3237)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3238)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3239)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3240)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3241)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3242)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3243)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3244)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3245)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3246)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3247)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3248)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3249)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3250)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3251)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3252)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3253)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3254)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3255)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3256)
- [GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG](https://github.com/vllm-project/vllm-torchtpu/pull/3267)
- [GitHub search · Alibaba · commits · willchan/bamboo · @willchan](https://github.com/willchan/bamboo/commit/63bb6b6bc5a0ede92ec572c167aa453dcacdf364)
- [GitHub search · Alibaba · pulls · willchan/bamboo · @willchan](https://github.com/willchan/bamboo/pull/31)
- [GitHub search · Alibaba · pulls · wyrd-company/ahp-pi-agent · @renovate[bot]](https://github.com/wyrd-company/ahp-pi-agent/pull/4)
- [GitHub search · Alibaba · pulls · xadupre/devdash-agents · @xadupre](https://github.com/xadupre/devdash-agents/pull/19)
- [GitHub search · Alibaba · pulls · zhongkaifu/TensorSharp · @zhongkaifu](https://github.com/zhongkaifu/TensorSharp/pull/371)
- [qwen-articles](https://qwen.ai/blog?id=8865c9dc-9833-4aa3-8c74-81c244bec7b0)

## نشانه‌ها