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