Qwen 2.5 Models — Hardware Requirements
29 Qwen 2.5 models from Alibaba and the community, from the smallest that runs in 0.5 GB of VRAM up to 72.7B parameters. Every row links to full quantization tables and GPU compatibility.
All Qwen 2.5 Models by Size
| Model | Params | Runs from | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| Qwen2.5 0.5B Instruct | 494M | 0.5 GB | 33K | ||
| Qwen2.5 0.5B | 494M | 0.5 GB | 33K | ||
| Qwen2.5 Coder 0.5B | 494M | 0.5 GB | 33K | ||
| Qwen2.5 Coder 1.5B | 1.5B | 1 GB | 33K | ||
| Qwen2.5 1.5B Instruct | 1.5B | 0.8 GB | 33K | ||
| Qwen2.5 Coder 1.5B Instruct | 1.5B | 1.0 GB | 33K | ||
| Qwen2.5 1.5B | 1.5B | 1 GB | 131K | ||
| Qwen2.5 1.5B Quantized.w8a8 | 1.8B | 1.1 GB | 33K | ||
| Qwen2.5 Omni 3B MNN | 3B | 6.6 GB | — | ||
| Qwen2.5 3B Instruct | 3.1B | 1.4 GB | 33K | ||
| Qwen2.5 Coder 3B Instruct | 3.1B | 1.4 GB | 33K | ||
| Qwen2.5 Coder 3B | 3.1B | 1.4 GB | 33K | ||
| Qwen2.5 3B | 3.1B | 1.6 GB | 33K | ||
| Qwen2.5 7B Instruct | 7.6B | 2.7 GB | 33K | ||
| Qwen2.5 Coder 7B Instruct | 7.6B | 3.0 GB | 33K | ||
| Qwen2.5 Coder 7B | 7.6B | 3.6 GB | 33K | ||
| Qwen2.5 7B | 7.6B | 3.6 GB | 131K | ||
| Qwen2.5 7B Instruct Uncensored | 7.6B | 3.6 GB | 33K | ||
| Qwen2.5 Coder 14B Instruct | 14.8B | 5.1 GB | 33K | ||
| Qwen2.5 14B Instruct | 14.8B | 5.1 GB | 33K | ||
| Qwen2.5 14B | 14.8B | 6.8 GB | 131K | ||
| Qwen2.5 Coder 14B | 14.8B | 7.0 GB | 33K | ||
| Qwen2.5 32B Instruct | 32.8B | 9.8 GB | 33K | ||
| Qwen2.5 Coder 32B Instruct | 32.8B | 9.8 GB | 33K | ||
| Qwen2.5 Coder 32B | 32.8B | 9.8 GB | 33K | ||
| Qwen2.5 32B | 32.8B | 14.3 GB | 131K | ||
| Qwen2.5 72B Instruct | 72.7B | 21.0 GB | 33K | ||
| Qwen2.5 72B | 72.7B | 31.0 GB | 131K | ||
| Qwen2.5 72B Instruct Abliterated | 72.7B | 31.9 GB | 33K |
How Qwen 2.5 Compares — Benchmark Rating
Qwen2.5 72B Instruct is the highest-rated Qwen 2.5 model with an overall benchmark rating of 49.4/100 — #38 among 75 open models. The top proprietary model, GPT 5.5, scores 88.8. Click a model to see its full benchmark breakdown.
GPT 5.5 · proprietary88.8
Claude Opus 4.7 · proprietary87.6
Claude Fable 5 · proprietary86.6
GPT 5.4 · proprietary86.6
Claude Opus 4.8 · proprietary84.4
DeepSeek V4 Pro77.5
Qwen3.6 27B74.0
StableBeluga269.1
MiniMax M2.768.4
Frequently Asked Questions
- How much VRAM do I need to run a Qwen 2.5 model?
- The smallest Qwen 2.5 model, Qwen2.5 0.5B Instruct, runs from 0.5 GB of VRAM at an aggressive quantization. Larger family members need proportionally more — see the table above for every model.
- Which Qwen 2.5 models can I run on a 16 GB GPU?
- 26 of 29 Qwen 2.5 models fit in 16 GB of VRAM at some quantization, including Qwen2.5 7B Instruct, Qwen2.5 32B Instruct, Qwen2.5 Coder 7B Instruct.
- What is the most popular Qwen 2.5 model to run locally?
- Qwen2.5 7B Instruct is the most downloaded Qwen 2.5 model in local-friendly quantized formats. It runs from 2.7 GB of VRAM.
- How do Qwen 2.5 models score on benchmarks?
- Qwen2.5 72B Instruct leads the family with an overall benchmark rating of 49.4/100, ranking #38 among 75 open models, while the top proprietary model, GPT 5.5, scores 88.8. See the comparison chart above for the full standings.