mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-i1-GGUF
AI model · https://huggingface.co/mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-i1-GGUF
First seen by Oriel on .
AI summary
This Hugging Face repository provides weighted/imatrix GGUF quantizations of DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic, spanning 2.8 GB to 7.5 GB with varying quality and performance trade-offs.
- The repository includes a 0.1 GB imatrix file for creating custom quantizations.
- The listed quants range from i1-IQ1_S at 2.8 GB, described as "for the desperate," to i1-Q6_K at 7.5 GB.
- i1-Q4_K_S is labeled optimal for size, speed, and quality, while the 5.7 GB i1-Q4_K_M is fast and recommended.
- IQ-quants are often preferred over similarly sized non-IQ variants, with several table notes identifying superior alternatives.
- Because this is a vision model, any mmproj files are hosted in the separate static quantization repository.
#gguf #model quantization #vision models #deepseek
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: 302, latest observation ; +185 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: 314,842, latest observation ; +258,643 over observed period since
Aliases
| Source | External ID | URL |
|---|---|---|
| Hugging Face Models | mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-i1-GGUF | https://huggingface.co/mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-i1-GGUF Read discussion |