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