Qwen3.5-35B-A3B needs about 23.2 GB of memory at Q4_K_M (a 22.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 10.7 GB (IQ2_XXS) to 69.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Qwen3.5-35B-A3B: 35B parameter vision‑language model with Mixture‑of‑Experts
Qwen3.5-35B-A3B is a 35 billion parameter model with 3 billion active experts. It supports vision and text, trained on 262 144 token context. The model is released under Apache‑2.0 and is compatible with llama.cpp and other inference engines.
Good at
- Vision‑language reasoning
- Long‑context text generation
- Multilingual support
Limits
- Requires large VRAM for full precision
- No native audio support
- License is Apache‑2.0
Best for
- Multimodal chat applications
- Large‑scale document summarization
- AI research prototypes
Who it’s for. Developers and researchers needing a high‑capacity vision‑language model for local inference. The model is suitable for environments where GPU memory is sufficient to run the chosen quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 10.7 GB | 11.8 GB | Too big | Get file → | |
| IQ2_M | 11.4 GB | 12.6 GB | Too big | Get file → | |
| Q2_K_XL | 12.2 GB | 13.3 GB | Too big | Get file → | |
| IQ3_XXS | 13.1 GB | 14.3 GB | Too big | Get file → | |
| IQ3_S | 13.6 GB | 14.8 GB | Too big | Get file → | |
| Q3_K_S | 15.3 GB | 16.4 GB | Too big | Get file → | |
| Q3_K_M | 16.4 GB | 17.5 GB | Too big | Get file → | |
| Q3_K_XL | 16.6 GB | 17.8 GB | Too big | Get file → | |
| IQ4_XS | 17.5 GB | 18.7 GB | Too big | Get file → | |
| IQ4_NL | 17.8 GB | 19.0 GB | Too big | Get file → | |
| Q4_K_L | 20.2 GB | 21.4 GB | Too big | Get file → | |
| Q4_K_S | 20.7 GB | 21.8 GB | Too big | Get file → | |
| MXFP4_MOE | 21.6 GB | 22.8 GB | Too big | Get file → | |
| Q4_K_M | 22.0 GB | 23.2 GB | Too big | Get file → | |
| Q4_K_XL | 22.2 GB | 23.4 GB | Too big | Get file → | |
| Q5_K_S | 24.8 GB | 26.0 GB | Too big | Get file → | |
| Q5_K_M | 26.2 GB | 27.4 GB | Too big | Get file → | |
| Q5_K_XL | 26.4 GB | 27.6 GB | Too big | Get file → | |
| Q6_K_S | 28.5 GB | 29.7 GB | Too big | Get file → | |
| Q6_K | 28.9 GB | 30.0 GB | Too big | Get file → | |
| Q6_K_XL | 32.1 GB | 33.2 GB | Too big | Get file → | |
| Q8_0 | 36.9 GB | 38.1 GB | Too big | Get file → | |
| Q8_K_XL | 48.7 GB | 49.9 GB | Too big | Get file → | |
| BF16 | 69.4 GB (2 parts) | 70.5 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_XXS (10.66 GB file, ~11.8 GB memory). For 16 GB VRAM, Q4_K_S (20.67 GB file, ~21.8 GB memory) or Q4_K_M (22.02 GB file, ~23.2 GB memory). For 24 GB VRAM, Q5_K_M (26.25 GB file, ~27.4 GB memory).
What GPU do you need for Qwen3.5-35B-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_XXS (10.7 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_S (13.6 GB file, about 14.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_XL (22.2 GB file, about 23.4 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (28.9 GB file, about 30.0 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (36.9 GB file, about 38.1 GB in use).
Which Qwen3.5-35B-A3B quant should you choose?
Q4_K_M is the usual starting point for Qwen3.5-35B-A3B: it balances file size and quality well. Here it is a 22.0 GB file.
The Q8_0 file is 36.9 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 IQ2_XXS at 10.7 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 Qwen3.5-35B-A3B
How much VRAM does Qwen3.5-35B-A3B need?
About 23.2 GB at Q4_K_M with an 8K context window. That is the 22.0 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 Qwen3.5-35B-A3B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwen3.5-35B-A3B GGUF?
It depends on the quant: IQ2_XXS is 10.7 GB, IQ2_M is 11.4 GB, Q2_K_XL is 12.2 GB, IQ3_XXS is 13.1 GB, IQ3_S is 13.6 GB, Q3_K_S is 15.3 GB and 18 more.
What context length does Qwen3.5-35B-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 Qwen3.5-35B-A3B GGUF?
The files are on Hugging Face in the unsloth/Qwen3.5-35B-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 Qwen3.5-35B-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 Qwen3.5-35B-A3B on 8 GB VRAM?
Use the IQ2_XXS quant, which requires about 11.8 GB of VRAM at 8k context. It is the smallest available quant for this model.
Does this model support vision tasks?
Yes, the model includes a vision encoder and is capable of image‑based reasoning and multimodal generation.
What license applies to this model?
The model is released under the Apache‑2.0 license, allowing free use and modification.