QW

Qwen3.5 2B coder

QwenGGUF by xprilionUpdated 2026-04-11
Download on Hugging Face
Parameters1.88B
Context256K
Layers24
Architectureqwen35
Smallest quant1.1 GB
Quick answer

Qwen3.5 2B coder 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 3 quants, from 1.1 GB (Q3_K_M) to 1.3 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

Qwen3.5 2B coder – a compact coding‑focused LLM

Qwen3.5 2B coder is a 1.88 billion‑parameter model fine‑tuned for coding, reasoning, tools, and vision tasks. It supports a 262144‑token context window and is available in multiple GGUF quantizations.

Good at

  • Coding assistance
  • Tool integration
  • Multimodal reasoning

Limits

  • No explicit license info
  • No vision support in text‑only mode
  • Requires 8 k context for memory estimates

Best for

  • Developers needing lightweight code generation
  • Researchers testing multimodal LLMs
  • Embedded systems with limited VRAM

Who it’s for. This model suits developers and researchers who need a small, efficient LLM for coding and multimodal tasks. It is ideal for environments where VRAM is constrained but a 262144‑token context is required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M1.1 GB 2.0 GB
Fits Get file →
Q4_01.2 GB 2.1 GB
Fits Get file →
Q4_K_M1.3 GB 2.2 GB
Fits Get file →

For 8 GB VRAM, use Q3_K_M (file size 1.1 GB, estimated 2 GB memory at 8 k context). If slightly more memory is available, Q4_0 (1.2 GB, 2.1 GB) or Q4_K_M (1.27 GB, 2.2 GB) can be used. Estimates are approximate.

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

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 Q4_K_M (1.3 GB file, about 2.2 GB in use).

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

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

If memory is tight, the smallest file is Q3_K_M at 1.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

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 byxprilion
FamilyQwen
Downloads (HF)1,337
Last updated2026-04-11

Frequently asked questions about Qwen3.5 2B coder

How much VRAM does Qwen3.5 2B coder 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 coder on an 8 GB GPU?

Yes, with Q4_K_M: the 1.3 GB file needs about 2.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: Q3_K_M is 1.1 GB, Q4_0 is 1.2 GB, Q4_K_M is 1.3 GB.

What context length does Qwen3.5 2B coder 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 coder GGUF?

The files are on Hugging Face in the xprilion/Qwen3.5-2B-coder repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Qwen3.5 2B coder on 8 GB VRAM?

Yes, the Q3_K_M quantization uses about 2 GB of VRAM at 8 k context, fitting within an 8 GB budget.

Does this model support vision tasks?

The model has detected vision abilities, but text‑only usage requires the llama‑cli; multimodal usage uses llama‑mtmd-cli.

What quantizations are available?

Available GGUF files are Q3_K_M, Q4_0, and Q4_K_M, with file sizes 1.1 GB, 1.2 GB, and 1.27 GB respectively.

Similar models

Browse all →

More Qwen models

All Qwen →

Other tiny models

All tiny models →