Qwen3.8

Zaman çizelgesi

1. 2026-11-13T19:07:40.219Z · Kanıt bağlantıları · GitHub search · Alibaba · commits · onprem-ai/deployment-catalog · @tomas-polach
2. 2026-11-13T19:07:40.219Z · Kanıt bağlantıları · GitHub search · Alibaba · commits · finereli/pyramid-mcp · @finereli
3. 2026-11-13T19:07:40.219Z · Kanıt bağlantıları · GitHub search · Alibaba · commits · fdietze/pi-infinite-context · @fdietze
4. 2026-11-13T19:07:40.219Z · Alex'in gönderileri · model ailesi · GitHub search · Alibaba · commits · agentgateway/agentgateway · @github-actions[bot]
   Alıntı

   json.providers.nebius.models["Qwen/Qwen3.8-27B"].name = "Qwen3.8 27B";

5. 2026-11-13T19:07:40.219Z · Kanıt bağlantıları · GitHub search · Alibaba · commits · aabhay007/Personal-AI-Core · @aabhay007
6. 2026-11-13T19:07:40.219Z · Kanıt bağlantıları · GitHub search · Alibaba · commits · QuantumKuba/Diffactly · @QuantumKuba
7. 2026-11-13T19:07:40.219Z · Kanıt bağlantıları · GitHub search · Alibaba · commits · Hallo-ich-bin-PeppaPig/Singularity · @Hallo-ich-bin-PeppaPig
8. 2026-11-13T19:07:40.219Z · Kanıt bağlantıları · GitHub search · Alibaba · commits · Azure/azureml-assets · @hanbitmyths
   Alıntı

   Add MAI, Qwen3.8 and Nemotron 3.5 Foundry Local coding models (#5452)

9. 2026-11-13T19:07:08.264Z · Alex'in gönderileri · model ailesi · GitHub search · Alibaba · pulls · xadupre/devdash-agents · @xadupre
   Alıntı

   - 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

10. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] qwen38_flash package entry: register() and READMEs

11. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] MTP draft model

12. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] KV offload pool regions

13. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] Runner input adapter

14. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] Hyper-connection layers

15. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] GDN layer input preparation

16. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] Pooled KV cache materialization

17. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] PD transfer: identity, manifest and Raiden connector

18. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] Config hook, geometry checks and pooled cache layout

19. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] PLE feature: tables, host lookup, storage, offload and pooled PLE

20. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] Sequence-parallel prefill backbone

21. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] QSA attention layer

22. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] Model-owned GDN op and layer (no register_oot)

23. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] Per-group Mamba index accessors

24. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] Mamba tail fold: export prefill checkpoints from inside the step

25. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] In-place rows update op

26. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] PLE Torch-to-JAX ops

27. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] QSA Torch-to-JAX ops

28. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] Torch bridge for the QSA kernels

29. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] GDN input preparation kernel

30. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] Unified KV pool kernels

31. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] PLE lookup and gate kernels

32. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] Hyper-connection kernels

33. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] Pooled QSA kernel over the unified KV pool

34. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] QSA KV write kernels (fused, main, compressed)

35. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] QSA union-walk kernels (plan, dense, SparseCore gather, prefill)

36. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] Qwen3.8-Flash model and registration hooks

37. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Alıntı

    [Model][Qwen3.8] QSA main-KV decode context parallelism over rank pairs (DCP-2) kernels

38. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vjmichael/Lu-AI-GUI · @vjmichael
    Alıntı

    - 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.

39. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · vitessio/vitess · @jdoupe
40. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · nearai/cvm-compose-files · @PierreLeGuen
41. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · michsindlinger/specwright · @michsindlinger
42. 2026-11-13T19:07:08.264Z · Alex'in gönderileri · model ailesi · GitHub search · Alibaba · pulls · SceneWorks/SceneWorks · @michaeltrefry
    Alıntı

    SW-7119: Qwen3.8 27B describer model and tier in core, worker, API and catalog

43. 2026-11-13T19:07:08.264Z · Alex'in gönderileri · model ailesi · GitHub search · Alibaba · pulls · NVIDIA/hyperflare-inference · @Raydius
    Alıntı

    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

44. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · FlashML-org/FreeToken · @zihaomu
45. 2026-11-13T19:07:08.264Z · Alex'in gönderileri · model ailesi · GitHub search · Alibaba · pulls · BuQQzz/SHIELD2.0 · @BuQQzz
    Alıntı

    Makes Qwen3.8 27B (IQ1_M) a working coding model on an 8 GB card (RTX 2070 SUPER) through SHIELD's own llama-server.

46. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · Azure/azureml-assets · @hanbitmyths
    Alıntı

    Add MAI, Qwen3.8 and Nemotron 3.5 Foundry Local coding models

47. 2026-11-13T19:07:08.264Z · Kanıt bağlantıları · GitHub search · Alibaba · pulls · 0xburden/modelship · @0xburden
    Alıntı

    - 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

48. 2026-11-05T17:57:47.304Z · Kanıt bağlantıları · GitHub · QwenLM/qwen-code · PR
    Alıntı

    - The Standard preset has the same qwen3.8 effort and GLM thinking gaps and will be aligned in a follow-up

49. 2026-09-17T18:25:45.043Z · Alex'in gönderileri · model ailesi · Alex Getman
    Alıntı

    🚨 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

50. 2026-08-26T12:54:00.791Z · Alex'in gönderileri · model ailesi · Alex Getman
    Alıntı

    🚨 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.

51. 2026-08-26T11:23:48.753Z · Alex'in gönderileri · model ailesi · Alex Getman
    Alıntı

    🚨 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.

52. 2026-08-18T05:00:00.000Z · Alex'in gönderileri · Alex Getman
    Alıntı

    ⚡️ 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.

53. 2026-08-14T18:14:16.552Z · Alex'in gönderileri · Alex Getman
    Alıntı

    ⚡️ 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.

54. 2026-07-19T11:07:11.687Z · Alex'in gönderileri · Alex Getman
    Alıntı

    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.