DeepSeek-V4-Pro-Qwen3.5-9B models released on Hugging Face

Two distinct versions of the DeepSeek-V4-Pro-Qwen3.5-9B model are available on Hugging Face, each with slightly different naming conventions. The first, hosted by 'mradermacher', is presented as an uncensored, heretical variant optimized for various local inference tools like llama.cpp, Ollama, and Docker. The second, from 'xtools-at', is also an uncensored, heretical model, but it appears to be multimodal and is compatible with inference servers such as vLLM and SGLang, with instructions provided for both. AI

IMPACT Provides users with options for running advanced language models locally, catering to different inference preferences and technical setups.

RANK_REASON The cluster describes the release and usage instructions for two distinct, fine-tuned versions of a large language model on Hugging Face.

Read on Hugging Face Trending Models →

• Google Colab
• Hugging Face
• Kaggle
• SGLang
• transformers
• vLLM
• xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic
• DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic
• Docker
• llama.cpp
• mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-i1-GGUF
• Ollama

• model release

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →