Alex Getmansinais antecipados de IA
PT

Qwen3.8 Flash Next

Alibaba

Lançado Atualizado
Janela de contexto
262K
262.144 tokens
Entrada / Saída
imagem, texto, vídeo → texto

Cronologia

  1. · Pesos abertos · link de referência
  2. · Disponibilidade na API · link de referência
  3. · Versão dos pesos · link de referência
  1. · Links de referência · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Excerto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  2. · Links de referência · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Excerto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  3. · Links de referência · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Excerto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  4. · Links de referência · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Excerto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  5. · Links de referência · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Excerto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  6. · Links de referência · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Excerto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  7. · Links de referência · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Excerto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  8. · Links de referência · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Excerto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  9. · Links de referência · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Excerto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  10. · Links de referência · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Excerto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  11. · Links de referência · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Excerto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  12. · Links de referência · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Excerto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  13. · Links de referência · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Excerto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  14. · Links de referência · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Excerto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  15. · Links de referência · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Excerto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  16. · Links de referência · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Excerto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  17. · Links de referência · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Excerto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  18. · Links de referência · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Excerto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  19. · Links de referência · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Excerto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  20. · Links de referência · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Excerto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  21. · Links de referência · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Excerto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  22. · Links de referência · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Excerto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  23. · Links de referência · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Excerto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  24. · Links de referência · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Excerto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  25. · Links de referência · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Excerto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  26. · Links de referência · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Excerto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  27. · Links de referência · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Excerto
    Part of the Qwen3.8-Flash-Next model directory (Experimental tier),
  28. · Links de referência · GitHub search · Alibaba · pulls · microsoft/onnxruntime-genai · @tianleiwu
    Excerto
    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. · Links de referência · GitHub search · Alibaba · pulls · TnzGit/dsh-superagent-prototype · @TnzGit
    Excerto
    - 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. · Links de referência · GitHub search · Alibaba · pulls · Azure/azureml-assets · @hanbitmyths
    Excerto
    | Qwen3.8-Flash-Next | 256K tokens | 61 GiB |
  31. · Uso confirmado · Qwen · official article bodies · Qwen3.8-Flash-Next: A New Architecture, Towards Ultimate Cost-Efficiency
Especificações

Qwen3.8 Flash Next é um modelo de Alibaba com pesos abertos, lançado em 2026-08-03. A janela de contexto é de 262.144 tokens.

Janela de contexto
262.144
Entrada
imagem · texto · vídeo
Saída
texto
Pesos
Abertos

Perguntas

Qual é a janela de contexto do Qwen3.8 Flash Next?

A janela de contexto é de 262.144 tokens.

O Qwen3.8 Flash Next tem pesos abertos?

Sim. Alibaba disponibiliza os pesos.

Quando o Qwen3.8 Flash Next foi lançado?

Em 2026-08-03.