Tem um workflow do ComfyUI? Gere uma documentação legível direto no navegador.Torne um workflow legível.Experimentar agora ↗
> Join the Discord for updates, roadmaps, projects, or just to chat.
Fonte do modelo
Descrição da fonte
Join the Discord for updates, roadmaps, projects, or just to chat.
Qwen3.5-4B uncensored by HauhauCS.
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.
Fontes
1 fonteVerificado 28 de jul.
Artefatos de modelo
5 artefatosTrechos de fonte
2 trechosThese are meant to be the best lossless uncensored models out there.
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.
| File | Quant | Size |
|---|---|---|
| Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-BF16.gguf | BF16 | 7.9 GB |
| Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-Q8_0.gguf | Q8_0 | 4.2 GB |
| Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-Q6_K.gguf | Q6_K | 3.3 GB |
| Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf | Q4_K_M | 2.6 GB |
| mmproj-Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-BF16.gguf | Vision encoder | 645 MB |
Vision support: This model is natively multimodal. The mmproj file is the vision encoder — you need it alongside the main GGUF to use image/video inputs. Load both files in llama.cpp, LM Studio, or any compatible runtime.
From the official Qwen authors:
Thinking mode (default):
temperature=0.6, top_p=0.95, top_k=20, min_p=0Non-thinking mode:
temperature=0.7, top_p=0.8, top_k=20, min_p=0Important:
Note: This is a brand new architecture (released 2026-03-02). llama.cpp support landed very recently — make sure you're on a recent build. Works with llama.cpp, LM Studio, Jan, koboldcpp, etc.
Also check out the 9B variant and all releases at HauhauCS.
Works with llama.cpp, LM Studio, Jan, koboldcpp, etc.
Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf
gguf · 2,52 GB · SHA-256 79e28ecacf84…2741 · Hugging Face
BaixarQwen3.5-4B-Uncensored-HauhauCS-Aggressive-Q6_K.gguf
gguf · 3,23 GB · SHA-256 ba93c2130085…b75f · Hugging Face
BaixarQwen3.5-4B-Uncensored-HauhauCS-Aggressive-Q8_0.gguf
gguf · 4,17 GB · SHA-256 3aa21dfc1855…0c16 · Hugging Face
Baixar--- license: apache-2.0 tags: - uncensored - qwen3.5 - qwen - gguf language: - en - zh - multilingual --- # Qwen3.5-4B-Uncensored-HauhauCS-Aggressive > **[Join the Discord](https://discord.gg/SZ5vacTXYf)** for updates, roadmaps, projects, or just to chat. Qwen3.5-4B uncensored by HauhauCS. ## 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. ## Downloads | File | Quant | Size | |------|-------|------| | Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-BF16.gguf | BF16 | 7.9 GB | | Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-Q8_0.gguf | Q8_0 | 4.2 GB | | Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-Q6_K.gguf | Q6_K | 3.3 GB | | Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf | Q4_K_M | 2.6 GB | | mmproj-Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-BF16.gguf | Vision encoder | 645 MB | **Vision support:** This model is natively multimodal. The `mmproj` file is the vision encoder — you need it alongside the main GGUF to use image/video inputs. Load both files in llama.cpp, LM Studio, or any compatible runtime. ## Specs - 4B 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 [Qwen3.5-4B](https://huggingface.co/Qwen/Qwen3.5-4B) ## 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` **Important:** - Maintain at least 128K context to preserve thinking capabil...
Source context: 143864 downloads · 448 likes · Repo HauhauCS/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive