176 likesNew · 10d old
New 9B Uncensored Model Packs Multiple GGUF Quantizations
What is DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-i1-GGUF?
The DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic model is a 9-billion-parameter language model with vision support, released in a variety of GGUF quantizations for llama.cpp. The repository offers files from a 2.8 GB “desperate” IQ1 quant up to a 7.5 GB Q6_K version, letting you trade size for quality.
Who it is for
Anyone who wants a locally-run, uncensored LLM that can also handle images can pick the appropriate GGUF file and run it with llama.cpp.
The story so far
Early Signal first spotted mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-i1-GGUF on November 7, 2026, with 176 likes. On its busiest day it gained 33 likes. The project is 10 days old. Early Signal files it under LLMs, Inference.