DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-i1-GGUF trending on Hugging Face
Original title: mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-i1-GGUF — new model trending #30 on Hugging Face
GGUF quantized uncensored DeepSeek model trending at #30 on Hugging Face.
mradermacher uploaded a GGUF quantized version of DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic to Hugging Face. The model is trending at position 30. Multiple quantization levels from 2.8GB to 5.9GB are provided for varying hardware.
- Multiple GGUF quants from 2.8GB to 5.9GB
- Imatrix file for custom quantization
- Uncensored heretic variant available
- Vendors
- mradermacher
From the original article
2 min read at huggingface.co<! -- ### quants: Q2_K IQ3_M Q4_K_S IQ3_XXS Q3_K_M small-IQ4_NL Q4_K_M IQ2_M Q6_K IQ4_XS Q2_K_S IQ1_M Q3_K_S IQ2_XXS Q3_K_L IQ2_XS Q5_K_S IQ2_S IQ1_S Q5_K_M Q4_0 IQ3_XS Q4_1 IQ3_S --> weighted/imatrix quants of https://huggingface. co/xtools-at/DeepSeek-V4-Pro-Qwen3.
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.