Qwen3.8
Alibaba
समयरेखा
सक्रिय निगरानी में नहीं है। इस नाम से रिलीज़ या नाम बदलने की पुष्टि नहीं हुई है।
- · संदर्भ लिंक · GitHub search · Alibaba · commits · onprem-ai/deployment-catalog · @tomas-polach
- · संदर्भ लिंक · GitHub search · Alibaba · commits · finereli/pyramid-mcp · @finereli
- · संदर्भ लिंक · GitHub search · Alibaba · commits · fdietze/pi-infinite-context · @fdietze
- · Alex की पोस्ट · श्रृंखला · GitHub search · Alibaba · commits · agentgateway/agentgateway · @github-actions[bot]
अंश
json.providers.nebius.models["Qwen/Qwen3.8-27B"].name = "Qwen3.8 27B";
- · संदर्भ लिंक · GitHub search · Alibaba · commits · aabhay007/Personal-AI-Core · @aabhay007
- · संदर्भ लिंक · GitHub search · Alibaba · commits · QuantumKuba/Diffactly · @QuantumKuba
- · संदर्भ लिंक · GitHub search · Alibaba · commits · Hallo-ich-bin-PeppaPig/Singularity · @Hallo-ich-bin-PeppaPig
- · संदर्भ लिंक · GitHub search · Alibaba · commits · Azure/azureml-assets · @hanbitmyths
अंश
Add MAI, Qwen3.8 and Nemotron 3.5 Foundry Local coding models (#5452)
- · Alex की पोस्ट · श्रृंखला · GitHub search · Alibaba · pulls · xadupre/devdash-agents · @xadupre
अंश
- 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
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] qwen38_flash package entry: register() and READMEs
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] MTP draft model
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] KV offload pool regions
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] Runner input adapter
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] Hyper-connection layers
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] GDN layer input preparation
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] Pooled KV cache materialization
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] PD transfer: identity, manifest and Raiden connector
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] Config hook, geometry checks and pooled cache layout
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] PLE feature: tables, host lookup, storage, offload and pooled PLE
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] Sequence-parallel prefill backbone
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] QSA attention layer
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] Model-owned GDN op and layer (no register_oot)
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] Per-group Mamba index accessors
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] Mamba tail fold: export prefill checkpoints from inside the step
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] In-place rows update op
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] PLE Torch-to-JAX ops
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] QSA Torch-to-JAX ops
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] Torch bridge for the QSA kernels
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] GDN input preparation kernel
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] Unified KV pool kernels
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] PLE lookup and gate kernels
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] Hyper-connection kernels
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] Pooled QSA kernel over the unified KV pool
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] QSA KV write kernels (fused, main, compressed)
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] QSA union-walk kernels (plan, dense, SparseCore gather, prefill)
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] Qwen3.8-Flash model and registration hooks
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
अंश
[Model][Qwen3.8] QSA main-KV decode context parallelism over rank pairs (DCP-2) kernels
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vjmichael/Lu-AI-GUI · @vjmichael
अंश
- 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.
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · vitessio/vitess · @jdoupe
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · nearai/cvm-compose-files · @PierreLeGuen
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · michsindlinger/specwright · @michsindlinger
- · Alex की पोस्ट · श्रृंखला · GitHub search · Alibaba · pulls · SceneWorks/SceneWorks · @michaeltrefry
अंश
SW-7119: Qwen3.8 27B describer model and tier in core, worker, API and catalog
- · Alex की पोस्ट · श्रृंखला · GitHub search · Alibaba · pulls · NVIDIA/hyperflare-inference · @Raydius
अंश
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
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · FlashML-org/FreeToken · @zihaomu
- · Alex की पोस्ट · श्रृंखला · GitHub search · Alibaba · pulls · BuQQzz/SHIELD2.0 · @BuQQzz
अंश
Makes Qwen3.8 27B (IQ1_M) a working coding model on an 8 GB card (RTX 2070 SUPER) through SHIELD's own llama-server.
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · Azure/azureml-assets · @hanbitmyths
अंश
Add MAI, Qwen3.8 and Nemotron 3.5 Foundry Local coding models
- · संदर्भ लिंक · GitHub search · Alibaba · pulls · 0xburden/modelship · @0xburden
अंश
- 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
- · संदर्भ लिंक · GitHub · QwenLM/qwen-code · PR
अंश
- The Standard preset has the same qwen3.8 effort and GLM thinking gaps and will be aligned in a follow-up
- · Alex की पोस्ट · श्रृंखला · Alex Getman
अंश
🚨 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
- · Alex की पोस्ट · श्रृंखला · Alex Getman
अंश
🚨 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.
- · Alex की पोस्ट · श्रृंखला · Alex Getman
अंश
🚨 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.
- · Alex की पोस्ट · Alex Getman
अंश
⚡️ 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.
- · Alex की पोस्ट · Alex Getman
अंश
⚡️ 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.
- · Alex की पोस्ट · Alex Getman
अंश
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.
विनिर्देश
Qwen3.8 · सक्रिय निगरानी में नहीं है। इस नाम से रिलीज़ या नाम बदलने की पुष्टि नहीं हुई है।
प्रश्न
Qwen3.8 कब जारी हुआ?
रिलीज़ की तारीख की पुष्टि नहीं