QW

Qwen2.5 3B

QwenGGUF by mradermacherUpdated 2026-01-16
Download on Hugging Face
Parameters3.4B
Context32K
Layers36
Architectureqwen2
Smallest quant0.0 GB
Quick answer

Qwen2.5 3B needs about 2.9 GB of memory at Q4_K_M (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 2.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.

LLDS‑tuned Qwen2.5‑3B‑Base for tool‑integrated reasoning

LLDS‑tuned Qwen2.5‑3B‑Base is a 3.4 billion‑parameter model optimized for tool‑integrated reinforcement learning. It supports search‑style inference with a local retrieval server. The model is released under Apache‑2.0.

Good at

  • Tool‑integrated search
  • Multi‑step reasoning
  • QA with local retrieval

Limits

  • No vision support
  • Requires local retriever for full functionality
  • Context limited to 32768 tokens

Best for

  • Research on tool‑integrated RL
  • Building retrieval‑augmented assistants
  • Testing LLDS regularization

Who it’s for. Researchers and developers working on tool‑integrated reinforcement learning who need a lightweight, open‑source model. The model is suitable for experimentation with search‑style inference pipelines.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.8 GB
Fits Get file →
IQ1_S0.9 GB 1.7 GB
Fits Get file →
IQ1_M1.0 GB 1.8 GB
Fits Get file →
IQ2_XXS1.1 GB 1.9 GB
Fits Get file →
IQ2_XS1.1 GB 1.9 GB
Fits Get file →
IQ2_S1.2 GB 2.0 GB
Fits Get file →
IQ2_M1.3 GB 2.1 GB
Fits Get file →
Q2_K_S1.3 GB 2.1 GB
Fits Get file →
Q2_K1.4 GB 2.2 GB
Fits Get file →
IQ3_XXS1.4 GB 2.2 GB
Fits Get file →
IQ3_XS1.5 GB 2.3 GB
Fits Get file →
Q3_K_S1.6 GB 2.4 GB
Fits Get file →
IQ3_S1.6 GB 2.4 GB
Fits Get file →
IQ3_M1.6 GB 2.4 GB
Fits Get file →
Q3_K_M1.7 GB 2.5 GB
Fits Get file →
Q3_K_L1.8 GB 2.6 GB
Fits Get file →
IQ4_XS1.9 GB 2.7 GB
Fits Get file →
IQ4_NL2.0 GB 2.8 GB
Fits Get file →
Q4_02.0 GB 2.8 GB
Fits Get file →
Q4_K_S2.0 GB 2.8 GB
Fits Get file →
Q4_K_M2.1 GB 2.9 GB
Fits Get file →
Q4_12.2 GB 3.0 GB
Fits Get file →
Q5_K_S2.4 GB 3.2 GB
Fits Get file →
Q5_K_M2.4 GB 3.2 GB
Fits Get file →
Q6_K2.8 GB 3.6 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (2.1 GB file, ~2.9 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (2.44 GB file, ~3.2 GB memory) offers a balance of size and performance. Larger VRAM allows Q6_K (2.79 GB file, ~3.6 GB memory).

What GPU do you need for Qwen2.5 3B?

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 Q6_K (2.8 GB file, about 3.6 GB in use).

Which Qwen2.5 3B quant should you choose?

Q4_K_M is the usual starting point for Qwen2.5 3B: it balances file size and quality well. Here it is a 2.1 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters3.4B
Layers36
Trained context32,768 tokens
KV cache (fp16)36 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseapache-2.0
Downloads (HF)690
Last updated2026-01-16

Frequently asked questions about Qwen2.5 3B

How much VRAM does Qwen2.5 3B need?

About 2.9 GB at Q4_K_M with an 8K context window. That is the 2.1 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 on an 8 GB GPU?

Yes, with Q6_K: the 2.8 GB file needs about 3.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen2.5 3B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 0.9 GB, IQ1_M is 1.0 GB, IQ2_XXS is 1.1 GB, IQ2_XS is 1.1 GB, IQ2_S is 1.2 GB and 19 more.

What context length does Qwen2.5 3B 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 GGUF?

The files are on Hugging Face in the mradermacher/LLDS-R-GRPO-Qwen2.5-3B-Base-i1-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 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 this model on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 2.9 GB of VRAM at 8k context, which fits within an 8 GB budget.

Does the model support vision?

No, the model has no vision capabilities.

What license applies?

The model is released under the Apache‑2.0 license.

Other GGUFs of LLDS-R-GRPO-Qwen2.5-3B-Base

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other tiny models

All tiny models →