QW

qwen2.5 3b instruct.Q4 K M

QwenGGUF by r1r21nbUpdated 2026-02-21
Download on Hugging Face
Parameters3.09B
Context32K
Layers36
Architectureqwen2
Smallest quant1.9 GB
Quick answer

qwen2.5 3b instruct.Q4 K M needs about 2.7 GB of memory at Q4_K_M (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 1.2 GB.

Qwen2.5 3B Instruct fine‑tuned for security research

This model is a 3.09 billion‑parameter Qwen2.5 instruction‑tuned variant, fine‑tuned for security research. It supports up to 32768 context tokens and is licensed under MIT. The model is available in a Q4_K_M quantized GGUF file.

Good at

  • Tools usage
  • Instruction following
  • Long‑context generation up to 8K tokens

Limits

  • No vision support
  • Requires 8K context for memory estimate
  • No mixture of experts

Best for

  • Security research queries
  • Red‑team operation planning
  • Exploit development guidance

Who it’s for. Developers and security researchers who need a compact, instruction‑tuned model for technical security questions. The model is lightweight and can run on consumer GPUs with limited VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.9 GB 2.7 GB
Fits Get file →

The Q4_K_M quantized file is 1.93 GB. It requires approximately 2.7 GB of VRAM at 8K context. This makes it suitable for GPUs with 4 GB or more of VRAM. For larger VRAM budgets, the same file can be used with lower context lengths to reduce memory usage.

What GPU do you need for qwen2.5 3b instruct.Q4 K M?

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 (1.9 GB file, about 2.7 GB in use).

Which qwen2.5 3b instruct.Q4 K M quant should you choose?

Q4_K_M is the usual starting point for qwen2.5 3b instruct.Q4 K M: it balances file size and quality well. Here it is a 1.9 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters3.09B
Layers36
Trained context32,768 tokens
KV cache (fp16)36 KB per token

Source

Quantized byr1r21nb
FamilyQwen
Licensemit
Downloads (HF)688
Last updated2026-02-21

Frequently asked questions about qwen2.5 3b instruct.Q4 K M

How much VRAM does qwen2.5 3b instruct.Q4 K M need?

About 2.7 GB at Q4_K_M 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 qwen2.5 3b instruct.Q4 K M on an 8 GB GPU?

Yes, with Q4_K_M: the 1.9 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of qwen2.5 3b instruct.Q4 K M GGUF?

It depends on the quant: Q4_K_M is 1.9 GB.

What context length does qwen2.5 3b instruct.Q4 K M support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.2 GB at 32K.

Where can I download qwen2.5 3b instruct.Q4 K M GGUF?

The files are on Hugging Face in the r1r21nb/qwen2.5-3b-instruct.Q4_K_M.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 qwen2.5 3b instruct.Q4 K M use?

Hugging Face lists the license as mit. 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 this model on 8 GB VRAM?

Yes, the Q4_K_M file uses about 2.7 GB of VRAM at 8K context, so 8 GB is more than sufficient.

Does this model support vision?

No, the model does not have vision capabilities.

What license applies to this model?

The model is released under the MIT license.

Other GGUFs of Qwen2.5-3B-Instruct

Similar models

Browse all →

More Qwen models

All Qwen →

Other tiny models

All tiny models →