Qwen3.6 35B A3B Uncensored LocalAI needs about 12.8 GB of memory at IQ2_M (a 11.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Qwen3.6 35B A3B Uncensored LocalAI – 35B parameter LLM with vision support
Qwen3.6 35B A3B Uncensored LocalAI is a 35‑billion‑parameter language model built on the qwen35moe architecture. It includes vision capabilities and is released under the Apache‑2.0 license. The model is available in a single IQ2_M quantized GGUF file.
Good at
- Large context handling up to 262,144 tokens
- Vision‑enabled text and image tasks
- Uncensored content generation
Limits
- Requires ~12.8 GB VRAM at 8 k context
- Only one quant available (IQ2_M)
- No other language support listed
Best for
- Developers needing a vision‑capable 35B model
- Researchers testing large‑scale LLMs
- Applications requiring uncensored text generation
Who it’s for. This model is suited for developers and researchers who need a large, vision‑enabled language model and are comfortable working with a single quantization format. It is ideal for projects that can allocate sufficient GPU memory and require the flexibility of an uncensored model.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 11.7 GB | 12.8 GB | Too big | Get file → |
The only available quant is IQ2_M, which weighs 11.66 GB and requires about 12.8 GB of VRAM at 8 k context. For systems with 8 GB VRAM, this model is not feasible. For 12 GB or larger GPUs, IQ2_M is the recommended choice.
What GPU do you need for Qwen3.6 35B A3B Uncensored LocalAI?
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: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is IQ2_M (11.7 GB file, about 12.8 GB in use).
Which Qwen3.6 35B A3B Uncensored LocalAI quant should you choose?
IQ2_M (11.7 GB) is the middle option in this repository. 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
Source
Frequently asked questions about Qwen3.6 35B A3B Uncensored LocalAI
How much VRAM does Qwen3.6 35B A3B Uncensored LocalAI need?
About 12.8 GB at IQ2_M with an 8K context window. That is the 11.7 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 35B A3B Uncensored LocalAI on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwen3.6 35B A3B Uncensored LocalAI GGUF?
It depends on the quant: IQ2_M is 11.7 GB.
What context length does Qwen3.6 35B A3B Uncensored LocalAI 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 35B A3B Uncensored LocalAI GGUF?
The files are on Hugging Face in the weareapexcreators/Qwen3.6-35B-A3B-Uncensored-LocalAI 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 35B A3B Uncensored LocalAI 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 this model on 8 GB VRAM?
No, the IQ2_M quant requires approximately 12.8 GB of VRAM at 8 k context, exceeding an 8 GB limit.
Does this model support vision tasks?
Yes, the model has detected vision capabilities and can process image inputs.
What license applies to this model?
The model is released under the Apache‑2.0 license.