Qwen3.6 35B A3B needs about 15.9 GB of memory at Q3_K_S (a 14.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 10 quants, from 9.4 GB (IQ2_S) to 18.3 GB (Q4_K_S). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Qwen3.6‑35B‑A3B – a vision‑capable, 35B parameter LLM with 3B active experts
Qwen3.6‑35B‑A3B is a causal language model with a vision encoder. It contains 35 billion total parameters, of which 3 billion are active in the mixture‑of‑experts architecture. The model supports a native context length of 262,144 tokens and can be extended up to 1,010,000 tokens.
Good at
- Vision‑enabled text generation
- Large context handling
- Mixture‑of‑experts efficiency
Limits
- Requires 8 GB+ VRAM for full‑precision inference
- No native support for Ollama
- License is Apache‑2.0
Best for
- Vision‑augmented content creation
- Long‑form document analysis
- Agentic coding workflows
Who it’s for. Developers and researchers needing a vision‑capable LLM with large context and efficient expert routing. The model is suitable for applications that require high‑quality text generation and image understanding on capable hardware.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_S | 9.4 GB | 10.6 GB | Too big | Get file → | |
| Q3_K_S | 11.7 GB | 12.8 GB | Too big | Get file → | |
| Q3_K_S | 11.7 GB | 12.9 GB | Too big | Get file → | |
| IQ3_S | 13.0 GB | 14.2 GB | Too big | Get file → | |
| Q3_K_S | 14.7 GB | 15.9 GB | Too big | Get file → | |
| IQ3_S | 15.1 GB | 16.2 GB | Too big | Get file → | |
| Q4_K_S | 16.5 GB | 17.7 GB | Too big | Get file → | |
| IQ4_XS | 17.0 GB | 18.2 GB | Too big | Get file → | |
| IQ4_XS | 18.0 GB | 19.2 GB | Too big | Get file → | |
| Q4_K_S | 18.3 GB | 19.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_S (16.49 GB file, ~17.7 GB VRAM at 8 k context). For 12 GB VRAM, Q3_K_S (11.67 GB file, ~12.8 GB VRAM) is a good balance. If you have 16 GB VRAM, IQ4_XS (17.05 GB file, ~18.2 GB VRAM) provides higher quality with similar memory usage.
What GPU do you need for Qwen3.6 35B A3B?
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_S (9.4 GB file, about 10.6 GB in use).
- 16 GB VRAM: the best quant that fits is Q3_K_S (14.7 GB file, about 15.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_S (18.3 GB file, about 19.5 GB in use).
Which Qwen3.6 35B A3B quant should you choose?
Q3_K_S (14.7 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is IQ2_S at 9.4 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
Source
Frequently asked questions about Qwen3.6 35B A3B
How much VRAM does Qwen3.6 35B A3B need?
About 15.9 GB at Q3_K_S with an 8K context window. That is the 14.7 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 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwen3.6 35B A3B GGUF?
It depends on the quant: IQ2_S is 9.4 GB, Q3_K_S is 11.7 GB, Q3_K_S is 11.7 GB, IQ3_S is 13.0 GB, Q3_K_S is 14.7 GB, IQ3_S is 15.1 GB and 4 more.
What context length does Qwen3.6 35B A3B 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 GGUF?
The files are on Hugging Face in the byteshape/Qwen3.6-35B-A3B-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 35B A3B 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 Qwen3.6‑35B‑A3B on 8 GB VRAM?
Yes, using the Q4_K_S quantized model which requires about 17.7 GB VRAM at 8 k context, so 8 GB is insufficient. You need at least 16 GB VRAM for this quantization.
Does this model support vision tasks?
Yes, it includes a vision encoder and is vision‑capable as noted in the GGUF repo card.
What license applies to this model?
The model is released under the Apache‑2.0 license.