QW

Qwen3.5-2B

QwenGGUF by trubiskyUpdated 2026-10-10
Download on Hugging Face
Parameters1.88B
Context256K
Layers24
Architectureqwen35
Smallest quant0.7 GB
Quick answer

Qwen3.5-2B needs about 1.8 GB of memory at IQ2_M (a 0.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.7 GB (IQ1_M) to 1.0 GB (IQ3_M). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

Qwen3.5-2B: 2B‑parameter causal language model with vision encoder

Qwen3.5-2B is a 2B‑parameter causal language model that includes a vision encoder. It supports 262144 context tokens and is designed for prototyping, task‑specific fine‑tuning, and research. The model is released under the apache‑2.0 license.

Good at

  • Vision‑language tasks
  • Reasoning and coding
  • Agent‑style applications

Limits

  • No explicit vision support in quantized GGUF files
  • Large VRAM requirement for full context
  • No multilingual language list provided

Best for

  • Fine‑tuning on small datasets
  • Research prototypes
  • Low‑latency inference on GPUs with 8 GB VRAM

Who it’s for. Developers and researchers who need a compact vision‑language model for experimentation or fine‑tuning. The model is suitable for teams working on prototypes or specialized tasks where a 2B‑parameter size is sufficient.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_M0.7 GB 1.6 GB
Fits Get file →
IQ2_M0.9 GB 1.8 GB
Fits Get file →
IQ3_M1.0 GB 1.9 GB
Fits Get file →

For 8 GB VRAM, use IQ1_M (0.74 GB, 1.6 GB memory at 8k context). If 12 GB VRAM is available, IQ2_M (0.85 GB, 1.8 GB memory) offers a balance between size and performance. IQ3_M (1.04 GB, 1.9 GB memory) is best for 16 GB VRAM or higher.

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 IQ3_M (1.0 GB file, about 1.9 GB in use).

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

IQ2_M (0.9 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.

If memory is tight, the smallest file is IQ1_M at 0.7 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
Parameters1.88B
Layers24
Trained context262,144 tokens
KV cache (fp16)48 KB per token

Source

Quantized bytrubisky
FamilyQwen
Base modelQwen/Qwen3.5-2B
Licenseapache-2.0
Downloads (HF)2,545
Last updated2026-10-10

Frequently asked questions about Qwen3.5-2B

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

About 1.8 GB at IQ2_M with an 8K context window. That is the 0.9 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 Qwen3.5-2B on an 8 GB GPU?

Yes, with IQ3_M: the 1.0 GB file needs about 1.9 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: IQ1_M is 0.7 GB, IQ2_M is 0.9 GB, IQ3_M is 1.0 GB.

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 1.6 GB at 32K.

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

The files are on Hugging Face in the trubisky/Qwen3.5-2B-RCOL 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, the IQ1_M quantization is 0.74 GB and requires about 1.6 GB VRAM at 8k context, which fits in 8 GB.

Does the model support vision tasks?

The base model includes a vision encoder, but the provided GGUF files do not specify explicit vision support.

Other GGUFs of Qwen3.5-2B

Similar models

Browse all →

More from trubisky

All by trubisky →

More Qwen models

All Qwen →

Other tiny models

All tiny models →