Qwen Models — Hardware Requirements
23 Qwen models from Alibaba and the community, from the smallest that runs in 0.8 GB of VRAM up to 72.3B parameters. Every row links to full quantization tables and GPU compatibility.
All Qwen Models by Size
| Model | Params | Runs from | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| SpatialLM1.1 Qwen 0.5B | 604M | 1.5 GB | 33K | ||
| Qwen1.5 0.5B Chat | 620M | 0.8 GB | 33K | ||
| Nemotron Research Reasoning Qwen 1.5B | 1.8B | 1.1 GB | 131K | ||
| Qwen1.5 1.8B Chat | 1.8B | 1.5 GB | 33K | ||
| Qwen 1 8B | 1.8B | 0.9 GB | 8K | ||
| Qwen1.5 1.8B | 1.8B | 1.5 GB | 33K | ||
| Qwen1.5 MoE A2.7B Chat | 2.7B | 1.9 GB | 33K | ||
| Qwen35 4B Soyuz Merged | 4B | 8.5 GB | 262K | ||
| CyberSecQwen 4B | 4.0B | 2.2 GB | 262K | ||
| CodeQwen1.5 7B | 7.3B | 3.5 GB | 66K | ||
| Qwen1.5 7B Chat | 7.7B | 4.7 GB | 33K | ||
| Qwen1.5 7B | 7.7B | 4.7 GB | 33K | ||
| Qwen 7B | 7.7B | 3.6 GB | 33K | ||
| Qwen Marketing | 8.2B | 18.0 GB | — | ||
| Qwen1.5 14B Chat | 14.2B | 8 GB | 33K | ||
| Qwen 14B Chat | 14.2B | 6.6 GB | 8K | ||
| Qwen 14B | 14.2B | 6.6 GB | 8K | ||
| Qwen1.5 14B | 14.2B | 8 GB | 33K | ||
| Qwen1.5 MoE A2.7B | 14.3B | 6.8 GB | 8K | ||
| Qwen27b Abliterated Fable MTP | 27B | 12.6 GB | — | ||
| Cogito V1 Preview Qwen 32B | 32B | 10.4 GB | 131K | ||
| XiYanSQL QwenCoder 32B 2504 | 32B | 14.4 GB | 33K | ||
| Qwen1.5 32B Chat | 32.5B | 14.3 GB | 33K | ||
| Qwen1.5 32B | 32.5B | 14.3 GB | 33K | ||
| Qwen AgentWorld 35B A3B | 34.7B | 9.9 GB | 262K | ||
| Qwen35B Agent R2 | 34.7B | 15.1 GB | 262K | ||
| Qwen35b Agent R2O3 | 34.7B | 15.1 GB | 262K | ||
| Qwen1.5 72B Chat | 72.3B | 35.5 GB | 33K |
How Qwen Compares — Benchmark Rating
Qwen 14B is the highest-rated Qwen model with an overall benchmark rating of 56.6/100 — #21 among 73 open models. The top proprietary model, Claude Fable 5 Max, scores 89.9. Click a model to see its full benchmark breakdown.
Claude Fable 5 Max · proprietary89.9
GPT 5.5 · proprietary89.2
GPT 5.6 Sol · proprietary89.2
Claude Fable 5 · proprietary88.6
Claude Opus 4.8 · proprietary88.1
GLM 5.282.7
Inkling79.2
DeepSeek V4 Pro74.3
Qwen3.6 27B74.0
Qwen 14B56.6
Qwen 14B Chat56.5
Qwen 7B41.1
Qwen 1 8B17.9
Frequently Asked Questions
- How much VRAM do I need to run a Qwen model?
- The smallest Qwen model, Qwen1.5 0.5B Chat, runs from 0.8 GB of VRAM at an aggressive quantization. Larger family members need proportionally more — see the table above for every model.
- Which Qwen models can I run on a 16 GB GPU?
- 26 of 28 Qwen models fit in 16 GB of VRAM at some quantization, including Qwen AgentWorld 35B A3B, Cogito V1 Preview Qwen 32B, Qwen1.5 0.5B Chat.
- What is the most popular Qwen model to run locally?
- Qwen AgentWorld 35B A3B is the most downloaded Qwen model in local-friendly quantized formats. It runs from 9.9 GB of VRAM.
- How do Qwen models score on benchmarks?
- Qwen 14B leads the family with an overall benchmark rating of 56.6/100, ranking #21 among 73 open models, while the top proprietary model, Claude Fable 5 Max, scores 89.9. See the comparison chart above for the full standings.