Qwen3.5 4B needs about 4.3 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 4 quants, from 2.7 GB (Q4_K_M) to 8.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Qwen3.5 4B – Pure GGUF quantized model with vision and reasoning
Qwen3.5 4B is a 4.21 B parameter causal language model with vision encoder. It supports reasoning, tools, and vision. The model is available in several GGUF quantizations and is licensed under Apache 2.0.
Good at
- Reasoning and coding
- Vision‑language tasks
- Tool use
Limits
- No vision without mmproj-f16.gguf
- Requires 8–12 GB VRAM for Q4_K_M
- Context length limited to 262144 tokens
Best for
- Chatbots needing multimodal input
- Code generation with visual context
- Agent instruction following
Who it’s for. Developers and researchers who need a lightweight, pure GGUF version of Qwen3.5 4B with vision support. The model is suitable for local inference on GPUs with 8–12 GB VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.7 GB | 4.3 GB | Fits | Get file → | |
| Q5_K_M | 3.1 GB | 4.6 GB | Fits | Get file → | |
| Q8_0 | 4.5 GB | 6.1 GB | Fits | Get file → | |
| F16 | 8.4 GB | 10.0 GB | Too big | Get file → |
For 8–12 GB VRAM, use Q4_K_M (2.71 GB file, ~4.3 GB memory at 8k context). If you have 12 GB or more, Q5_K_M (3.07 GB, ~4.6 GB) or Q8_0 (4.48 GB, ~6.1 GB) give higher quality. F16 is too large for most setups.
What GPU do you need for Qwen3.5 4B?
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: the best quant that fits is Q5_K_M (3.1 GB file, about 4.6 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 6.1 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (8.4 GB file, about 10.0 GB in use).
Which Qwen3.5 4B quant should you choose?
Q4_K_M is the usual starting point for Qwen3.5 4B: it balances file size and quality well. Here it is a 2.7 GB file.
The Q8_0 file is 4.5 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen3.5 4B
How much VRAM does Qwen3.5 4B need?
About 4.3 GB at Q4_K_M with an 8K context window. That is the 2.7 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 Qwen3.5 4B on an 8 GB GPU?
Yes, with Q8_0: the 4.5 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3.5 4B GGUF?
It depends on the quant: Q4_K_M is 2.7 GB, Q5_K_M is 3.1 GB, Q8_0 is 4.5 GB, F16 is 8.4 GB.
What context length does Qwen3.5 4B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Qwen3.5 4B GGUF?
The files are on Hugging Face in the Smoffyy/Qwen3.5-4B-Instruct-Pure-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 4B 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 4B on 8 GB VRAM?
Yes, Q4_K_M fits within 8–12 GB VRAM and uses about 4.3 GB memory at 8k context.
Does the model support vision?
Vision requires the separate mmproj-f16.gguf file; without it the model runs only as a text model.
What license applies to this model?
The model is released under Apache 2.0, with all derivatives also under Apache 2.0.