Qwen3.6-35B-A3B needs about 23.9 GB of memory at Q4_K_M (a 22.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 22 quants, from 11.4 GB (IQ1_M) to 71.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
Qwen3.6-35B-A3B: 35B parameter LLM with vision and MoE
Qwen3.6-35B-A3B is a causal language model with a vision encoder. It contains 35 billion total parameters, 3 billion active in the mixture‑of‑experts architecture, and supports a native context length of 262,144 tokens, extendable to over a million tokens.
Good at
- Vision‑enabled text generation
- Large context handling
- Mixture‑of‑experts efficiency
Limits
- Requires 8 k context for memory estimates
- Large file sizes for high‑precision quants
- No explicit vision‑only mode
Best for
- Vision‑augmented coding assistants
- Long‑form document analysis
- Complex multimodal reasoning
Who it’s for. Developers and researchers needing a versatile, vision‑capable LLM with a large context window. The model is suitable for applications that benefit from the mixture‑of‑experts design and post‑training fine‑tuning.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_M | 11.4 GB | 12.6 GB | Too big | Get file → | |
| IQ2_XXS | 11.8 GB | 13.0 GB | Too big | Get file → | |
| IQ2_M | 11.9 GB | 13.1 GB | Too big | Get file → | |
| Q2_K_XL | 12.6 GB | 13.8 GB | Too big | Get file → | |
| IQ3_XXS | 14.1 GB | 15.3 GB | Too big | Get file → | |
| IQ3_S | 15.3 GB | 16.5 GB | Too big | Get file → | |
| Q3_K_M | 17.1 GB | 18.3 GB | Too big | Get file → | |
| Q3_K_XL | 17.2 GB | 18.4 GB | Too big | Get file → | |
| IQ4_XS | 18.2 GB | 19.4 GB | Too big | Get file → | |
| IQ4_NL | 18.5 GB | 19.7 GB | Too big | Get file → | |
| Q4_K_S | 21.4 GB | 22.6 GB | Too big | Get file → | |
| MXFP4_MOE | 22.2 GB | 23.4 GB | Too big | Get file → | |
| Q4_K_M | 22.7 GB | 23.9 GB | Too big | Get file → | |
| Q4_K_XL | 22.9 GB | 24.0 GB | Too big | Get file → | |
| Q5_K_S | 25.5 GB | 26.7 GB | Too big | Get file → | |
| Q5_K_M | 27.1 GB | 28.3 GB | Too big | Get file → | |
| Q5_K_XL | 27.2 GB | 28.3 GB | Too big | Get file → | |
| Q6_K | 30.0 GB | 31.2 GB | Too big | Get file → | |
| Q6_K_XL | 32.6 GB | 33.8 GB | Too big | Get file → | |
| Q8_0 | 37.8 GB | 39.0 GB | Too big | Get file → | |
| Q8_K_XL | 39.1 GB | 40.3 GB | Too big | Get file → | |
| BF16 | 71.1 GB (2 parts) | 72.3 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_M (11.37 GB) or IQ2_XXS (11.82 GB). With 12 GB VRAM, IQ2_M (11.88 GB) or Q2_K_XL (12.57 GB) are suitable. For 16 GB VRAM, Q3_K_M (17.1 GB) or Q3_K_XL (17.23 GB) provide a balance of size and performance.
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: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is IQ3_XXS (14.1 GB file, about 15.3 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_XL (22.9 GB file, about 24.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (30.0 GB file, about 31.2 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_K_XL (39.1 GB file, about 40.3 GB in use).
Which Qwen3.6-35B-A3B quant should you choose?
Q4_K_M is the usual starting point for Qwen3.6-35B-A3B: it balances file size and quality well. Here it is a 22.7 GB file.
The Q8_0 file is 37.8 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is IQ1_M at 11.4 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 23.9 GB at Q4_K_M with an 8K context window. That is the 22.7 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 12.6 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: IQ1_M is 11.4 GB, IQ2_XXS is 11.8 GB, IQ2_M is 11.9 GB, Q2_K_XL is 12.6 GB, IQ3_XXS is 14.1 GB, IQ3_S is 15.3 GB and 16 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 2.8 GB at 32K.
Where can I download Qwen3.6-35B-A3B GGUF?
The files are on Hugging Face in the unsloth/Qwen3.6-35B-A3B-MTP-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?
Use the IQ1_M or IQ2_XXS quantized files, each around 11–12 GB, which fit within 8 GB VRAM when accounting for overhead.
Does the model support vision tasks?
Yes, the model includes a vision encoder and is detected to have vision capabilities.
What context length does the model support?
The native context length is 262,144 tokens, extendable up to 1,010,000 tokens.