Almost Fully Uncensored Qwen3.5-9B Model Published on Hugging Face
Almost Fully Uncensored Qwen3.5-9B Model Published on Hugging Face
The model DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED was fine-tuned on 250,000 examples and then modified to reduce refusals; its Q4-quantized version weighs about 5.6 GB.
Almost Fully Uncensored Qwen3.5-9B Model Published on Hugging Face
The model is named DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED. According to the developers, it was first fine-tuned on 250,000 math and natural-science examples generated by DeepSeek-V4-Pro, and then modified so that it refuses requests less often.
In the author's test of 100 prompts, the original model refused 100 times, while the modified version refused only 3 times.
The model has 9 billion parameters. The Q4-quantized version weighs about 5.6 GB, so it can run locally on an ordinary computer.
Why it matters
AnalysisThe release shows that small local AI models can be tuned to minimize refusals, which may be useful for private workflows but requires careful safety evaluation.
Discuss in community
Share your questions and insights with developers
Related in Ecosystem
Practical guides, core terminology, and agent skills
GPT Image Generative Models Prompting Guide
OpenAI's gpt-image generative models are designed to produce production-quality visuals and fully controllable creative workflows. They are suitable for both professional design ta...
Claude Sonnet 4.6 vs GPT-5.5 vs Gemini 3.1 Pro: 2026 model comparison
Every few weeks, a new model comes out, and every time the same questions arise: should I switch? what changed what to pay for?
Thinking Machines Releases Inkling 2 Small: a 594B MoE Model That Can Fine-Tune Other Models
Thinking Machines released Inkling 2 Small, a 594B-parameter MoE model that leads among open models in several benchmarks and demonstrated autonomous fine-tuning of Qwen3.5-4B.
GGUF & Modern Quantization Standards
The GGUF format is a universal binary file format for storing and instantaneously loading quantized language models on CPUs and GPUs in llama.cpp, Ollama, and LM Studio.