MiniCPM Models — Hardware Requirements

12 MiniCPM models from OpenBMB and the community, from the smallest that runs in 0.5 GB of VRAM up to 8x2B parameters. Every row links to full quantization tables and GPU compatibility.

All MiniCPM Models by Size

ModelParamsContext
MiniCPM5 2B DSpark324M131K
MiniCPM5 1B CoreAI1B—
MiniCPM5 1B Claude Opus Fable5 v2 Thinking1.1B131K
MiniCPM5 1B Agentic Tooluse Merged FP161.1B131K
Huihui MiniCPM5 1B Abliterated1.1B131K
MiniCPM5 1B1.1B131K
MiniCPM5 1B Base1.1B131K
MiniCPM5 1B SFT1.1B131K
MiniCPM5 1B Claude Opus Fable5 v2 Thinking Heretic1.1B131K
MiniCPM V 4.61.3B262K
MiniCPM V 4.6 Thinking1.3B262K
MiniCPM 2B Sft BF162B4K
MiniCPM5 2B2.5B131K
MiniCPM5 2B Base2.5B524K
MiniCPM5 2B SFT2.5B131K
MiniCPM5 2B Midtrain2.5B131K
Minicpm5 2B Distilled Reasoning2.5B131K
MiniCPM O 2 68.7B33K
MiniCPM V 4 58.7B41K
MiniCPM O 4 59.4B41K
MiniCPM SALA9.5B524K
MiniCPM MoE 8x2B8x2B4K

Frequently Asked Questions

How much VRAM do I need to run a MiniCPM model?
The smallest MiniCPM model, MiniCPM5 2B DSpark, 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 MiniCPM models can I run on a 16 GB GPU?
21 of 22 MiniCPM models fit in 16 GB of VRAM at some quantization, including MiniCPM5 1B Claude Opus Fable5 v2 Thinking, MiniCPM O 4 5, MiniCPM V 4 5.
What is the most popular MiniCPM model to run locally?
MiniCPM SALA is the most downloaded MiniCPM model in local-friendly quantized formats. It runs from 19.3 GB of VRAM.