Hugging Face's logo

infosave
/
Qwen3.8-Flash-Next-Fast-Code-cmf

Text Generation
cortiq
English
Russian
Chinese
cmf
quantized
q4tp
Mixture of Experts
code
expert-pruning
speculative-decoding
vulkan
cuda
Model card Files
xet
 Community
Qwen3.8-Flash-Next-Fast-Code-cmf / assets

Commit History

Yesterday

  1. Card by backend: CUDA (12 GB and up) and Vulkan (48 GB and up) as separate sections, one figure per stand

    infosave
    Verified signature
    d181f41

  2. Card: requirements, install, run and settings for every card; no aquarium

    infosave
    Verified signature
    ab077e6

  3. cortiq 0.8.78: cards from 12 GB at 91-97 % of Strata Coder with 4-bit experts

    infosave
    Verified signature
    feff033

  4. CUDA on cards from 12 GB: 105 / 118 / 133 tok/s within 12 / 16 / 24 GB

    infosave
    Verified signature
    04344f2

4 days ago

  1. Card: the task-aware cut (fcaq256), aquarium page, new figures

    infosave
    Verified signature
    817ef23

  2. Upload assets/fc_speed_zh.png with huggingface_hub

    infosave
    Verified signature
    65ddf5b

  3. Upload assets/fc_speed_ru.png with huggingface_hub

    infosave
    Verified signature
    be832fc

  4. Upload assets/fc_speed_en.png with huggingface_hub

    infosave
    Verified signature
    c874448

  5. Upload assets/fc_size_zh.png with huggingface_hub

    infosave
    Verified signature
    9a45bb2

  6. Upload assets/fc_size_ru.png with huggingface_hub

    infosave
    Verified signature
    3fedabb

  7. Upload assets/fc_size_en.png with huggingface_hub

    infosave
    Verified signature
    846f564

  8. Upload assets/fc_quality_zh.png with huggingface_hub

    infosave
    Verified signature
    fa108d0

  9. Upload assets/fc_quality_ru.png with huggingface_hub

    infosave
    Verified signature
    2c4eeb3

  10. Upload assets/fc_quality_en.png with huggingface_hub

    infosave
    Verified signature
    8e8553d