Model fiche
Qwen 2.5 Coder 3B Instruct
By Alibaba · China
code
small
Overview
Alibaba's 3B Qwen 2.5 Coder hitting HumanEval 84.1, covering 92 programming languages. Restricted to non-commercial use under the Qwen Research License.
When to pick this model
- Personal coding assistant on 4–8GB VRAM
- Academic research on small code models
- On-device completion where the 1.5B isn't strong enough
- Side projects under the Qwen Research License
VRAM requirements by quantization
| Quantization | VRAM required |
|---|---|
| Q4_K_M (recommended) | 2 GB |
| Q5_K_M | 2.5 GB |
| Q8_0 | 4 GB |
| FP16 (no quantization) | 6 GB |
VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.
Strengths
- HumanEval 84.1 — exceptional for 3B
- Around 2GB VRAM at Q4
- Fast inline completion
- 92 programming languages
Limitations
- Qwen Research License blocks commercial use
- 32k context only
- Trails the 7B Coder on complex multi-file tasks
Architecture & training
Architecture: Dense · 3B · Qwen 2.5 Coder · code-optimized
Training: 3B params code-optimized, 92 programming languages.
Verdict
Best-in-class 3B coder benchmark-wise, but the non-commercial license pushes most teams to the Apache 2.0 1.5B or 14B variants.
Quick start
ollama run qwen2.5-coder:3bOr use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.
Tools
Is Qwen 2.5 Coder 3B Instruct the right pick for you?