mradermacher publishes GGUF quants of gemma-4-31B-it-ARA-heretic
Original title: mradermacher/gemma-4-31B-it-ARA-heretic-GGUF — new model trending #30 on Hugging Face
Static GGUF files from Q2_K through Q8_0, plus mmproj supplements, are listed as the repo trends at #30.
mradermacher released static GGUF quantizations of richardyoung/gemma-4-31B-it-ARA-heretic, now trending #30 on Hugging Face. The repo lists sizes from Q2_K at 12.0 GB to Q8_0 at 32.7 GB, plus mmproj-Q8_0 and mmproj-f16 multi-modal supplements. Weighted imatrix quants are pointed to a separate i1-GGUF repository. Usage notes refer readers to TheBloke GGUF READMEs.
- Q4_K_S and Q4_K_M are marked fast and recommended.
- Q6_K is labeled very good quality; Q8_0 is labeled best quality.
- Q3_K_M is noted as lower quality.
- mmproj files are 0.9 GB and 1.3 GB multi-modal supplements.
- nethype GmbH is thanked for providing server capacity.
- Products
- gemma-4-31B-it-ARA-heretic-GGUF
- Organizations
- nethype GmbH
- AI models
- gemma-4-31B-it-ARA-heretic
From the original article
1 min read at huggingface.co<! -- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS --> static quants of https://huggingface. co/richardyoung/gemma-4-31B-it-ARA-heretic ***For a convenient overview and download list, visit our [model page for this model](https://hf.
By mradermacher · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.