QW

Qwen3.5-2B

QwenGGUF by unslothUpdated 2026-05-16
Download on Hugging Face
Parameters1.94B
Context256K
Layers25
Architectureqwen35
Smallest quant0.9 GB
Quick answer

Qwen3.5-2B needs about 2.2 GB of memory at Q4_K_M (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 21 quants, from 0.9 GB (IQ2_M) to 3.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.7 GB.

Qwen3.5‑2B: 2 B‑parameter vision‑language model in GGUF format

Qwen3.5‑2B is a 2 B‑parameter causal language model with a vision encoder. It supports 262,144‑token context and is trained for multimodal tasks. The model is released under Apache‑2.0 and is suitable for prototyping and fine‑tuning.

Good at

  • Vision‑language reasoning
  • Multilingual text generation
  • Efficient inference with MTP

Limits

  • No native vision support in llama.cpp without MTP
  • Requires 8 k context for memory estimates
  • Large VRAM needed for higher‑quality quants

Best for

  • Local vision‑language inference on 8 GB VRAM
  • Fine‑tuning for specific multimodal tasks
  • Rapid prototyping of multimodal agents

Who it’s for. Developers and researchers who need a lightweight vision‑language model for local deployment. The model is ideal for prototyping, task‑specific fine‑tuning, and research in multimodal AI.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M0.9 GB 1.9 GB
Fits Get file →
IQ3_XXS1.0 GB 1.9 GB
Fits Get file →
Q2_K_XL1.1 GB 2.0 GB
Fits Get file →
Q3_K_S1.1 GB 2.0 GB
Fits Get file →
Q3_K_M1.1 GB 2.1 GB
Fits Get file →
Q3_K_XL1.2 GB 2.1 GB
Fits Get file →
IQ4_XS1.3 GB 2.2 GB
Fits Get file →
Q4_01.3 GB 2.2 GB
Fits Get file →
Q4_K_S1.3 GB 2.2 GB
Fits Get file →
IQ4_NL1.3 GB 2.2 GB
Fits Get file →
Q4_K_M1.3 GB 2.2 GB
Fits Get file →
Q4_11.3 GB 2.3 GB
Fits Get file →
Q4_K_XL1.4 GB 2.3 GB
Fits Get file →
Q5_K_S1.4 GB 2.4 GB
Fits Get file →
Q5_K_M1.5 GB 2.4 GB
Fits Get file →
Q5_K_XL1.5 GB 2.4 GB
Fits Get file →
Q6_K1.6 GB 2.5 GB
Fits Get file →
Q6_K_XL1.9 GB 2.8 GB
Fits Get file →
Q8_02.1 GB 3.0 GB
Fits Get file →
Q8_K_XL2.9 GB 3.8 GB
Fits Get file →
BF163.9 GB 4.8 GB
Fits Get file →

For 8 GB VRAM, use Q4_0 or Q4_K_S (≈2.2 GB model size, ~2.2 GB VRAM usage). If 12 GB VRAM is available, Q5_K_M or Q6_K provide higher quality while staying under 3 GB VRAM. For maximum quality with 16 GB VRAM, Q8_0 is recommended.

What GPU do you need for Qwen3.5-2B?

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 Q8_K_XL (2.9 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is BF16 (3.9 GB file, about 4.8 GB in use).

Which Qwen3.5-2B quant should you choose?

Q4_K_M is the usual starting point for Qwen3.5-2B: it balances file size and quality well. Here it is a 1.3 GB file.

The Q8_0 file is 2.1 GB, about 1.6 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_M at 0.9 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

Architectureqwen35
Parameters1.94B
Layers25
Trained context262,144 tokens
KV cache (fp16)50 KB per token

Source

Quantized byunsloth
FamilyQwen
Base modelQwen/Qwen3.5-2B
Licenseapache-2.0
Downloads (HF)18,893
Last updated2026-05-16

Frequently asked questions about Qwen3.5-2B

How much VRAM does Qwen3.5-2B need?

About 2.2 GB at Q4_K_M with an 8K context window. That is the 1.3 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 Qwen3.5-2B on an 8 GB GPU?

Yes, with BF16: the 3.9 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3.5-2B GGUF?

It depends on the quant: IQ2_M is 0.9 GB, IQ3_XXS is 1.0 GB, Q2_K_XL is 1.1 GB, Q3_K_S is 1.1 GB, Q3_K_M is 1.1 GB, Q3_K_XL is 1.2 GB and 15 more.

What context length does Qwen3.5-2B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.7 GB at 32K.

Where can I download Qwen3.5-2B GGUF?

The files are on Hugging Face in the unsloth/Qwen3.5-2B-MTP-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 Qwen3.5-2B 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 Qwen3.5‑2B on 8 GB VRAM?

Yes, using Q4_0 or Q4_K_S quantization, which require about 2.2 GB VRAM at 8 k context.

Does this model support vision tasks in llama.cpp?

Vision support requires the MTP speculative decoding branch; otherwise only text inference is available.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Qwen3.5-2B

Similar models

Browse all →

More from unsloth

All by unsloth →

More Qwen models

All Qwen →

Other tiny models

All tiny models →