Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

keptn
/
gemma4-31b-a4

Image-Text-to-Text
radiance
radiance-2
rocm
amd
rdna4
4-bit precision
int4
int8
w4a8
gptq
speculative-decoding
mtp
vision
Model card Files Files and versions
xet
Community
gemma4-31b-a4
21.4 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 21 commits
keptn's picture
keptn
Card: shorter top, version history at the end, stale 1.x lines removed
1826864 verified 2 days ago
  • .gitattributes
    1.56 kB
    gemma4-31b-w4a8: radiance container about 1 month ago
  • LICENSE
    11.4 kB
    gemma4-31b-w4a8: radiance container about 1 month ago
  • README.md
    7.83 kB
    Card: shorter top, version history at the end, stale 1.x lines removed 2 days ago
  • config.json
    90 Bytes
    Version 2.0: a4 format (u4 with zero point, f16 scale per 128, int8 activations per 128), calibrated with keptn/quant-calibration-v1. Version 1.0 stays at revision v1.0 13 days ago
  • gemma4-31b-a4.rad
    21.4 GB
    xet
    Version 2.0: a4 format (u4 with zero point, f16 scale per 128, int8 activations per 128), calibrated with keptn/quant-calibration-v1. Version 1.0 stays at revision v1.0 13 days ago
  • gemma4-31b-a4.recipe
    23.2 kB
    Version 2.0: a4 format (u4 with zero point, f16 scale per 128, int8 activations per 128), calibrated with keptn/quant-calibration-v1. Version 1.0 stays at revision v1.0 13 days ago