QW

Qwen/Qwen3.5-9B

QwenGGUF by twoodyUpdated 2026-10-01
Download on Hugging Face
Parameters9.2B
Context256K
Layers33
Architectureqwen35
Smallest quant5.8 GB
Quick answer

Qwen/Qwen3.5-9B needs about 7.4 GB of memory at Q4_K_M (a 5.8 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.

Qwen3.5-9B GGUF model with vision support

Qwen3.5-9B is a 9.2B parameter causal language model with a vision encoder. It supports 262,144 token context and is released under apache-2.0. The GGUF file is quantised to Q4_K_M for efficient inference.

Good at

  • Reasoning
  • Tools usage
  • Vision tasks

Limits

  • Requires 7.4 GB VRAM at 8k context
  • Only Q4_K_M quantisation available
  • License is apache-2.0

Best for

  • Chatbots needing vision
  • Code generation with tool calls
  • Multimodal content creation

Who it’s for. Developers building local AI applications that need both language and image understanding. The model is ready to run with llama.cpp and supports a wide range of languages and tasks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M5.8 GB 7.4 GB
Tight Get file →

The single available quant is Q4_K_M, file size 5.78 GB. It needs about 7.4 GB VRAM for 8k context. For lower VRAM, consider using a higher quant like Q8_K if available, but it is not in the file list.

What GPU do you need for Qwen/Qwen3.5-9B?

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: the best quant that fits is Q4_K_M (5.8 GB file, about 7.4 GB in use).

Which Qwen/Qwen3.5-9B quant should you choose?

Q4_K_M is the usual starting point for Qwen/Qwen3.5-9B: it balances file size and quality well. Here it is a 5.8 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters9.2B
Layers33
Trained context262,144 tokens
KV cache (fp16)132 KB per token

Source

Quantized bytwoody
FamilyQwen
Base modelQwen/Qwen3.5-9B
Licenseapache-2.0
Downloads (HF)968
Last updated2026-10-01

Frequently asked questions about Qwen/Qwen3.5-9B

How much VRAM does Qwen/Qwen3.5-9B need?

About 7.4 GB at Q4_K_M with an 8K context window. That is the 5.8 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 Qwen/Qwen3.5-9B on an 8 GB GPU?

Yes, with Q4_K_M: the 5.8 GB file needs about 7.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen/Qwen3.5-9B GGUF?

It depends on the quant: Q4_K_M is 5.8 GB.

What context length does Qwen/Qwen3.5-9B 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 4.4 GB at 32K.

Where can I download Qwen/Qwen3.5-9B GGUF?

The files are on Hugging Face in the twoody/Qwen3.5-9B-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 Qwen/Qwen3.5-9B 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 Qwen3.5-9B on 8 GB VRAM?

The Q4_K_M quantisation requires about 7.4 GB VRAM at 8k context, so it fits within 8 GB but leaves little headroom.

Does the model support image input?

Yes, the vision part is provided as mmproj-F16.gguf, enabling image reading with llama.cpp.

What license applies to this model?

The model is released under apache-2.0, the same license as the original Qwen3.5-9B.

Other GGUFs of Qwen3.5-9B

Similar models

Browse all →

More from twoody

All by twoody →

More Qwen models

All Qwen →

Other small models

All small models →