Downloads · 30 days
109
2% of all-time downloads
stevelikesrhino/gemma-4-31B-it-nvfp4-GGUF
gemma-4-31B-it-nvfp4-GGUF is a text generation model from stevelikesrhino. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
- Used calibration text from Bartowski's gist: https://gist.github.com/bartowski1182/82ae9b520227f57d79ba04add13d0d0d - Used nvidia/Gemma-4-31B-IT-NVFP4 as base model - Template is using google/gemma-4-31B-it latest t…
Downloads · 30 days
109
2% of all-time downloads
All-time downloads
6.5K
Public
Repo size
85.3 GB
Likes
6
Public
Click a slice to open those files.
.gguf44 GB · 100%
From the Hugging Face model README
Key modification include quantizing swa's Wq Wk Wv and attention output into q8_0, but kept Wk and global attention output bf16.
Since nvfp4 significantly compressed the FFN tensors, resulting BPW is conveniently just over 6.
NVFP4 related tensors are untouched: weight scales for proper fp4 scaling are kept unchanged.
For image, get any of the mainstream mmproj-bf16 gguf.