Qwen 2.5 3B Instruct
Mid-edge Qwen 2.5. Note: 3B variant uses the Qwen Research License (not Apache 2.0), which is non-commercial.
Overview
Mid-edge Qwen 2.5. Note: 3B variant uses the Qwen Research License (not Apache 2.0), which is non-commercial.
Featured in this stack
The L3 execution stacks that pick this model as a recommended component, with the one-line note explaining the role it plays in each.
- Stack · L3·Homelab tier·Role: Multilingual 3B alternativeiPhone on-device AI stack — Llama 3.2 3B / Phi-3.5 Mini via MLX Swift
Qwen 2.5 3B at INT4 is the multilingual choice. Note Qwen License for the 3B size class (not Apache 2.0). Similar memory footprint as Llama 3.2 3B.
Family & lineage
How this model relates to others in its lineage. Family members share architecture and training-data roots; parent / children edges record direct distillation or fine-tune relationships.
Strengths
- Edge deployable
Weaknesses
- Qwen Research License (research or evaluation only; commercial use needs a license from Alibaba Cloud)
Quantization variants
Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.
| Quantization | File size | VRAM required |
|---|---|---|
| Q4_K_M | 1.9 GB | 4 GB |
Get the model
HuggingFace
Original weights
Source repository — direct quantization required.
Hardware that runs this
Cards with enough VRAM for at least one quantization of Qwen 2.5 3B Instruct.
Models worth comparing
Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.
Frequently asked
What's the minimum VRAM to run Qwen 2.5 3B Instruct?
Can I use Qwen 2.5 3B Instruct commercially?
What's the context length of Qwen 2.5 3B Instruct?
Source: huggingface.co/Qwen/Qwen2.5-3B-Instruct
Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.
Related — keep moving
Verify Qwen 2.5 3B Instruct runs on your specific hardware before committing money.