Hugging Face's logo

nvidia
/
GLM-5.3-Flash-NVFP4

Image-Text-to-Text
Safetensors
Model Optimizer
glm5_next
nvidia
ModelOpt
GLM-5
quantized
FP4
fp4
conversational
8-bit precision
modelopt
Model card Files
xet
 Community
15
GLM-5.3-Flash-NVFP4

Commit History

27 days ago

  1. fix: declare NextN (MTP) layer 45 as BF16 in quantization ignore lists (#11)⁠

    shengliangx +1: lucifer1004
    da920bb

  1. Add SGLang serving instructions (#5)⁠

    zhiyucheng +1: sh-25
    09b04e5

  1. Update README.md

    shengliangx
    Verified signature
    423acf3

  2. Update README.md

    shengliangx
    Verified signature
    2bd7b1c

  1. Update README.md

    shengliangx
    Verified signature
    52f93b7

  2. Create README.md

    shengliangx
    Verified signature
    90b7003

  3. GLM-5.3-Flash-NVFP4 (NVFP4 routed experts + dense MLP, FP8 KV cache)

    shengliangx
    9377ce9