mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUF
AI model · https://huggingface.co/mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUF
First seen by Oriel on .
AI summary
The Hugging Face page provides static GGUF quantizations of DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic, with file sizes and brief quality or speed recommendations.
- Available model quantizations range from Q2_K at 3.9 GB to f16 at 18.0 GB.
- Q4_K_S and Q4_K_M are marked fast and recommended; Q6_K is described as very good quality.
- Q8_0 is listed as fast with best quality, while f16 is described as overkill.
- The page also offers mmproj-Q8_0 and mmproj-f16 multimodal supplements.
- Weighted/imatrix quantizations are linked separately, and the page points users to GGUF usage guidance.
#gguf #llm 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: 209, latest observation ; +54 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: 499,655, latest observation ; +121,295 over observed period since
Aliases
| Source | External ID | URL |
|---|---|---|
| Hugging Face Models | mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUF | https://huggingface.co/mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUF Read discussion |