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