QW

Qwen3.5-4B

QwenGGUF by ISTA-DASLabUpdated 2026-05-26
Download on Hugging Face
Parameters4.21B
Context256K
Layers32
Architectureqwen35
Smallest quant1.9 GB
Quick answer

Qwen3.5-4B needs about 3.5 GB of memory at Q2_K_XL (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Qwen3.5-4B GGUF Q2_K_XL refined with GSQ

Qwen3.5-4B is a 4.21B parameter causal language model with a vision encoder. The GGUF Q2_K_XL checkpoint is 1.94 GB and uses GSQ refinement. It runs on llama.cpp, Ollama, and other GGUF consumers.

Good at

  • Vision‑language tasks
  • Reasoning and coding
  • Multilingual support

Limits

  • Requires 3.5 GB VRAM at 8k context
  • No explicit vision API support in llama.cpp
  • Apache‑2.0 license

Best for

  • Embedded inference on edge devices
  • Rapid prototyping with low‑precision models
  • Multilingual chatbot deployments

Who it’s for. Developers needing a compact vision‑language model for local inference. The model is suitable for projects that can run GGUF files and require multilingual and visual understanding capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K_XL1.9 GB 3.5 GB
Fits Get file →

The only available quant is Q2_K_XL, 1.94 GB on disk. It needs approximately 3.5 GB VRAM at 8k context. For 8 GB VRAM setups, this quant is a good fit. No higher‑precision options are listed.

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: the best quant that fits is Q2_K_XL (1.9 GB file, about 3.5 GB in use).

Which Qwen3.5-4B quant should you choose?

Q2_K_XL (1.9 GB) is the middle option in this repository. 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

Architectureqwen35
Parameters4.21B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byISTA-DASLab
FamilyQwen
Base modelQwen/Qwen3.5-4B
Licenseapache-2.0
Downloads (HF)1,484
Last updated2026-05-26

Frequently asked questions about Qwen3.5-4B

How much VRAM does Qwen3.5-4B need?

About 3.5 GB at Q2_K_XL with an 8K context window. That is the 1.9 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 Q2_K_XL: the 1.9 GB file needs about 3.5 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: Q2_K_XL is 1.9 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 ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ 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, the Q2_K_XL quant uses about 3.5 GB VRAM at 8k context, leaving headroom for other processes.

Does this model support vision tasks?

Yes, it is a causal language model with a vision encoder, enabling vision‑language inference.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Qwen3.5-4B

Similar models

Browse all →

More from ISTA-DASLab

All by ISTA-DASLab →

More Qwen models

All Qwen →

Other small models

All small models →