Qwen3.5-35B-A3B needs about 22.7 GB of memory at Q4_K_M (a 21.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.2 GB 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 multimodal LLM with vision and MoE
Qwen3.5-35B-A3B is a 35B parameter causal language model with vision encoder. It uses a mixture of experts architecture with 3B active parameters and a trained context length of 262144 tokens. The model is released under the apache-2.0 license.
Good at
- Vision‑language reasoning
- Large context handling
- Efficient inference with MoE
Limits
- Requires 8‑bit or higher quant for 8 GB VRAM
- No native support for 16‑bit precision in llama.cpp
- License restricts commercial redistribution without permission
Best for
- Multimodal chatbots
- Long‑form content generation
- Research on MoE architectures
Who it’s for. Developers and researchers building multimodal applications who need a large context window and efficient inference. The model is suitable for fine‑tuning and in‑context learning experiments.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.2 GB | 1.4 GB | Fits | Get file → | |
| Q2_K_M | 13.6 GB | 14.8 GB | Too big | Get file → | |
| IQ2_S | 14.0 GB | 15.2 GB | Too big | Get file → | |
| IQ2_XS | 14.3 GB | 15.5 GB | Too big | Get file → | |
| IQ2_M | 14.6 GB | 15.8 GB | Too big | Get file → | |
| IQ3_XXS | 16.4 GB | 17.6 GB | Too big | Get file → | |
| IQ3_XS | 16.6 GB | 17.8 GB | Too big | Get file → | |
| Q3_K_M | 17.5 GB | 18.7 GB | Too big | Get file → | |
| IQ3_M | 17.8 GB | 19.0 GB | Too big | Get file → | |
| IQ3_S | 17.8 GB | 19.0 GB | Too big | Get file → | |
| IQ4_XS | 18.7 GB | 19.8 GB | Too big | Get file → | |
| Q4_0 | 19.6 GB | 20.8 GB | Too big | Get file → | |
| IQ4_NL | 19.7 GB | 20.9 GB | Too big | Get file → | |
| Q4_K_M | 21.6 GB | 22.7 GB | Too big | Get file → | |
| Q4_1 | 21.8 GB | 22.9 GB | Too big | Get file → | |
| Q5_0 | 23.9 GB | 25.1 GB | Too big | Get file → | |
| Q5_K_M | 25.4 GB | 26.6 GB | Too big | Get file → | |
| Q5_1 | 26.1 GB | 27.3 GB | Too big | Get file → | |
| Q6_K_M | 28.5 GB | 29.7 GB | Too big | Get file → | |
| Q8_0 | 36.9 GB | 38.1 GB | Too big | Get file → | |
| BF16 | 63.1 GB (2 parts) | 64.2 GB | Too big | Get file → | |
| F16 | 63.1 GB (2 parts) | 64.2 GB | Too big | Get file → | |
| F16 | 69.4 GB (2 parts) | 70.5 GB | Too big | Get file → | |
| BF16 | 69.4 GB (2 parts) | 70.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (21.57 GB file, 22.7 GB memory at 8k context). For 16 GB VRAM, Q5_K_M (25.43 GB file, 26.6 GB memory) offers a good balance. If memory is limited to 4 GB, consider Q2_K_M (13.59 GB file, 14.8 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: the best quant that fits is the main file (0.2 GB file, about 1.4 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.4 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.4 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.4 GB in use).
- 16 GB VRAM: the best quant that fits is IQ2_M (14.6 GB file, about 15.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_1 (21.8 GB file, about 22.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K_M (28.5 GB file, about 29.7 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 21.6 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 the first one in the table at 0.2 GB, with the quality trade-offs that come with fewer bits.
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 22.7 GB at Q4_K_M with an 8K context window. That is the 21.6 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?
Yes, with the smaller files: the 0.2 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3.5-35B-A3B GGUF?
It depends on the quant: file is 0.2 GB, Q2_K_M is 13.6 GB, IQ2_S is 14.0 GB, IQ2_XS is 14.3 GB, IQ2_M is 14.6 GB, IQ3_XXS is 16.4 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 Mungert/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 Q4_K_M quantized file; it requires about 22.7 GB memory at 8k context, so 8 GB VRAM is insufficient for full inference.
Does the model support vision tasks?
Yes, the model includes a vision encoder and was trained with vision tokens.
What license applies to this model?
The model is released under the apache-2.0 license.