license: gemma
base_model: sakamakismile/Huihui-gemma-4-31B-it-qat-abliterated-MTP-NVFP4
library_name: gguf
tags:
- gguf
- gemma
- gemma4
- quantized
- llama-cpp
- lm-studio
- ollama
- conversational
Huihui Gemma 4 31B Abliterated MTP — GGUF
GGUF conversions ofsakamakismile/Huihui-gemma-4-31B-it-qat-abliterated-MTP-NVFP4.
These files are intended for GGUF-compatible runtimes such as
llama.cpp
Files
| File | Size |
|---|---|
Huihui-gemma-4-31B-it-qat-abliterated-MTP-BF16.gguf |
910.63 MB |
Huihui-gemma-4-31B-it-qat-abliterated-MTP-Q8_0.gguf |
490.86 MB |
Huihui-gemma-4-31B-it-qat-abliterated-NVFP4.gguf |
17.99 GB |
Huihui-gemma-4-31B-it-qat-abliterated-mmproj-BF16.gguf |
1.12 GB |
Huihui-gemma-4-31B-it-qat-abliterated-mmproj-F16.gguf |
1.12 GB |
Huihui-gemma-4-31B-it-qat-abliterated-mmproj-Q8_0.gguf |
772.04 MB |
Notes
- These are community GGUF conversions; refer to the source model card for
model lineage, intended behavior, limitations, and upstream credits. - The source model is abliterated. Use it responsibly and lawfully.
- The model remains subject to the Gemma license and terms.
- Compatibility and output quality can vary by runtime and quantization.
Credits
Original and upstream work is credited in the
source model card.