Alex Getmansegnali precoci sull'IA
IT

Qwen3.8 Flash Next

Alibaba

Rilasciato Aggiornato
Finestra di contesto
262K
262.144 token
Ingresso / Uscita
immagine, testo, video → testo

Cronologia

  1. · Pesi aperti · link di riscontro
  2. · Disponibilità API · link di riscontro
  3. · Versione dei pesi · link di riscontro
  1. · Link di riscontro · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Estratto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  2. · Link di riscontro · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Estratto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  3. · Link di riscontro · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Estratto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  4. · Link di riscontro · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Estratto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  5. · Link di riscontro · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Estratto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  6. · Link di riscontro · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Estratto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  7. · Link di riscontro · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Estratto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  8. · Link di riscontro · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Estratto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  9. · Link di riscontro · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Estratto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  10. · Link di riscontro · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Estratto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  11. · Link di riscontro · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Estratto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  12. · Link di riscontro · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Estratto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  13. · Link di riscontro · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Estratto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  14. · Link di riscontro · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Estratto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  15. · Link di riscontro · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Estratto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  16. · Link di riscontro · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Estratto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  17. · Link di riscontro · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Estratto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  18. · Link di riscontro · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Estratto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  19. · Link di riscontro · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Estratto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  20. · Link di riscontro · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Estratto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  21. · Link di riscontro · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Estratto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  22. · Link di riscontro · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Estratto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  23. · Link di riscontro · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Estratto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  24. · Link di riscontro · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Estratto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  25. · Link di riscontro · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Estratto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  26. · Link di riscontro · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Estratto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  27. · Link di riscontro · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Estratto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  28. · Link di riscontro · GitHub search · Alibaba · pulls · microsoft/onnxruntime-genai · @tianleiwu
    Estratto
    context-tier budget adaptation and hardware-aware `runtime_profiles` improvements for Qwen3.8-Flash-Next RC5 (`QMoE`) and GGUF (`MoEPacked`) hybrid offload across 16 GB, 24 GB, 32 GB, and H200
  29. · Link di riscontro · GitHub search · Alibaba · pulls · TnzGit/dsh-superagent-prototype · @TnzGit
    Estratto
    - Sanitized local-Agent verification (2026-11-08): Qwen3.8-Flash-Next on a local vLLM dev build had working tool calls and streaming; 8K/32K/64K were exercised without OOM. Short-response decode
  30. · Link di riscontro · GitHub search · Alibaba · pulls · Azure/azureml-assets · @hanbitmyths
    Estratto
    | Qwen3.8-Flash-Next | 256K tokens | 61 GiB |
  31. · Utilizzo confermato · Qwen · official article bodies · Qwen3.8-Flash-Next: A New Architecture, Towards Ultimate Cost-Efficiency
Specifiche

Qwen3.8 Flash Next è un modello di Alibaba con pesi aperti, rilasciato il 2026-08-03. La finestra di contesto è di 262.144 token.

Finestra di contesto
262.144
Ingresso
immagine · testo · video
Uscita
testo
Pesi
Aperti

Domande

Qual è la finestra di contesto di Qwen3.8 Flash Next?

La finestra di contesto è di 262.144 token.

Qwen3.8 Flash Next ha pesi aperti?

Sì. Alibaba pubblica i pesi.

Quando è stato rilasciato Qwen3.8 Flash Next?

Il 2026-08-03.