Yi Models — Hardware Requirements
5 Yi models from 01.AI and the community, from the smallest that runs in 2.9 GB of VRAM up to 34.4B parameters. Every row links to full quantization tables and GPU compatibility.
All Yi Models by Size
| Model | Params | Runs from | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| Yi 6B | 6.1B | 2.9 GB | 4K | ||
| Yi 6B Chat | 6.1B | 2.9 GB | 4K | ||
| Yi 9B | 8.8B | 4.1 GB | 4K | ||
| Yi 34B Chat | 34.4B | 15.0 GB | 4K | ||
| Yi 34B | 34.4B | 15.0 GB | 4K |
How Yi Compares — Benchmark Rating
Yi 34B is the highest-rated Yi model with an overall benchmark rating of 63.3/100 — #11 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
Yi 34B63.3
Yi 34B Chat47.0
Yi 6B Chat46.7
Yi 6B44.7
Frequently Asked Questions
- How much VRAM do I need to run a Yi model?
- The smallest Yi model, Yi 6B, runs from 2.9 GB of VRAM at an aggressive quantization. Larger family members need proportionally more — see the table above for every model.
- Which Yi models can I run on a 16 GB GPU?
- 5 of 5 Yi models fit in 16 GB of VRAM at some quantization, including Yi 34B Chat, Yi 6B, Yi 34B.
- What is the most popular Yi model to run locally?
- Yi 34B Chat is the most downloaded Yi model in local-friendly quantized formats. It runs from 15.0 GB of VRAM.
- How do Yi models score on benchmarks?
- Yi 34B leads the family with an overall benchmark rating of 63.3/100, ranking #11 among 75 open models, while the top proprietary model, GPT 5.5, scores 88.8. See the comparison chart above for the full standings.