Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-MLX-8bit

Qwen3.5-9B-Uncensored-HauhauCS-Aggressive

Qwen3.5-9B uncensored by HauhauCS.

Quality: quantized (8bit affine, group size: 32, 9.34 bpw)

About

0/465 refusals. Fully uncensored with zero capability loss.

No changes to datasets or capabilities. Fully functional, 100% of what the original authors intended - just without the refusals.

These are meant to be the best lossless uncensored models out there.

Aggressive Variant

Stronger uncensoring with more thorough refusal removal. If this variant is too loose for your use case, a Balanced variant may follow.

Note: The model is fully unlocked and will not refuse prompts. However, it may occasionally append a short disclaimer at the end of a response (e.g. "This is general information, not legal advice..."). This is baked into the base model's training and not a refusal — the actual content is still generated in full.

Specs

• 9B dense parameters, 32 layers
• Hybrid architecture: Gated DeltaNet linear attention + full softmax attention (3:1 ratio)
• 262K native context (extendable to 1M with YaRN)
• Natively multimodal (text, image, video)
• Multi-token prediction (MTP) support
• 248K vocabulary, 201 languages
• Based on Qwen3.5-9B

Also check out the 27B variant

Recommended Settings

From the official Qwen authors:

Thinking mode (default):

• temperature=0.6, top_p=0.95, top_k=20, min_p=0

Non-thinking mode:

• temperature=0.7, top_p=0.8, top_k=20, min_p=0

---

Source

This model was converted to MLX format from HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive