mradermacher/gemma-4-31B-it-ARA-heretic-GGUF
AI model · https://huggingface.co/mradermacher/gemma-4-31B-it-ARA-heretic-GGUF
First seen by Oriel on .
AI summary
This Hugging Face repository provides static GGUF quantizations of richardyoung/gemma-4-31B-it-ARA-heretic, with multiple size and quality options plus multimodal supplements.
- Quantized model files range from Q2_K at 12.0 GB to Q8_0 at 32.7 GB.
- Q4_K_S and Q4_K_M are marked fast and recommended, while Q6_K offers very good quality and Q8_0 provides the best quality.
- The repository includes mmproj-Q8_0 and mmproj-f16 multimodal supplements sized 0.9 GB and 1.3 GB, respectively.
- Weighted/imatrix quantizations are available separately in mradermacher/gemma-4-31B-it-ARA-heretic-i1-GGUF.
- Users unfamiliar with GGUF or concatenating multi-part files are directed to TheBloke's READMEs.
#gemma #gguf #model quantization #multimodal models
Generated by gpt-5.6-sol. Check the original for details.
Metric trends
Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained
Likes
Total likes reported by the source.
- Hugging Face Models: 359, latest observation ; +258 over observed period since
Downloads (30d)
Rolling 30-day downloads. A change in this value is not new downloads during the observed period.
- Hugging Face Models: 161,317, latest observation ; +159,229 over observed period since
Aliases
| Source | External ID | URL |
|---|---|---|
| Hugging Face Models | mradermacher/gemma-4-31B-it-ARA-heretic-GGUF | https://huggingface.co/mradermacher/gemma-4-31B-it-ARA-heretic-GGUF Read discussion |