QW

Qwen3.6 Uncensored Aggressive

QwenGGUF by tripolskypetrUpdated 2026-05-20
Download on Hugging Face
Parameters26.9B
Context256K
Layers40
Architectureqwen35moe
Smallest quant10.0 GB
Quick answer

Qwen3.6 Uncensored Aggressive needs about 22.3 GB of memory at Q4_K_M (a 21.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 10.0 GB (IQ2_M) to 43.6 GB (Q8_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Qwen3.6 Uncensored Aggressive – 26.9B parameter, vision‑enabled LLM

Qwen3.6 Uncensored Aggressive is a 26.9B parameter causal language model with vision encoder. It supports reasoning, tools, and vision tasks. The model is released under the apache-2.0 license and offers an uncensored variant with no refusals.

Good at

  • Vision‑enabled reasoning
  • Tool use
  • Large context handling

Limits

  • Large VRAM required for full precision
  • No safety guardrails – may produce unrestricted content
  • Requires 262144 token context for full capability

Best for

  • Vision‑based content creation
  • Tool‑integrated workflows
  • Large‑context document analysis

Who it’s for. Developers needing a fully uncensored, vision‑capable LLM for complex reasoning and tool integration. Suitable for applications that can handle unrestricted content and have sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M10.0 GB 11.2 GB
Too big Get file →
Q2_K11.5 GB 12.7 GB
Too big Get file →
IQ2_M11.7 GB 12.8 GB
Too big Get file →
IQ3_XS12.0 GB 13.1 GB
Too big Get file →
IQ3_M12.6 GB 13.8 GB
Too big Get file →
Q3_K14.3 GB 15.5 GB
Too big Get file →
Q2_K15.0 GB 16.2 GB
Too big Get file →
IQ4_XS15.1 GB 16.3 GB
Too big Get file →
IQ3_M15.4 GB 16.6 GB
Too big Get file →
Q4_K17.5 GB 18.7 GB
Too big Get file →
IQ4_XS18.7 GB 19.9 GB
Too big Get file →
Q3_K19.0 GB 20.2 GB
Too big Get file →
IQ4_NL19.8 GB 21.0 GB
Too big Get file →
Q5_K20.8 GB 22.0 GB
Too big Get file →
Q4_K_M21.2 GB 22.3 GB
Too big Get file →
Q6_K23.2 GB 24.3 GB
Too big Get file →
Q4_K23.4 GB 24.6 GB
Too big Get file →
Q5_K28.0 GB 29.2 GB
Too big Get file →
Q6_K30.6 GB 31.8 GB
Too big Get file →
Q8_K32.0 GB 33.1 GB
Too big Get file →
Q8_K43.6 GB 44.8 GB
Too big Get file →

For 8 GB VRAM, use IQ2_M (file size 10 GB, memory 11.2 GB at 8 k context). For 16 GB VRAM, Q2_K (file size 11.52 GB, memory 12.7 GB) or IQ3_XS (file size 11.97 GB, memory 13.1 GB). For 24 GB VRAM, Q4_K_M (file size 21.17 GB, memory 22.3 GB) is recommended. Memory estimates are approximate.

What GPU do you need for Qwen3.6 Uncensored Aggressive?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is IQ2_M (10.0 GB file, about 11.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q3_K (14.3 GB file, about 15.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (21.2 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (30.6 GB file, about 31.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_K (43.6 GB file, about 44.8 GB in use).

Which Qwen3.6 Uncensored Aggressive quant should you choose?

Q4_K_M is the usual starting point for Qwen3.6 Uncensored Aggressive: it balances file size and quality well. Here it is a 21.2 GB file.

If memory is tight, the smallest file is IQ2_M at 10.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters26.9B (approximate, mixture of experts)
Layers40
Trained context262,144 tokens
KV cache (fp16)80 KB per token

Source

Quantized bytripolskypetr
FamilyQwen
Licenseapache-2.0
Downloads (HF)577
Last updated2026-05-20

Frequently asked questions about Qwen3.6 Uncensored Aggressive

How much VRAM does Qwen3.6 Uncensored Aggressive need?

About 22.3 GB at Q4_K_M with an 8K context window. That is the 21.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Qwen3.6 Uncensored Aggressive on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3.6 Uncensored Aggressive GGUF?

It depends on the quant: IQ2_M is 10.0 GB, Q2_K is 11.5 GB, IQ2_M is 11.7 GB, IQ3_XS is 12.0 GB, IQ3_M is 12.6 GB, Q3_K is 14.3 GB and 15 more.

What context length does Qwen3.6 Uncensored Aggressive support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.

Where can I download Qwen3.6 Uncensored Aggressive GGUF?

The files are on Hugging Face in the tripolskypetr/Qwen3.6-Uncensored-Aggressive-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Qwen3.6 Uncensored Aggressive use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Q4_K_M on 8 GB VRAM?

No, Q4_K_M requires about 22.3 GB of VRAM at 8 k context, which exceeds 8 GB.

Does the model support vision tasks?

Yes, it includes a vision encoder and is capable of vision‑related reasoning.

Is the model licensed for commercial use?

Yes, it is released under the apache-2.0 license, which allows commercial use.

Other GGUFs of Qwen3.6-35B-A3B

Similar models

Browse all →

More from tripolskypetr

All by tripolskypetr →

More Qwen models

All Qwen →

Other medium models

All medium models →