openbmb · First MLX build 10 Sept 2026
MiniCPM5-2B
MLX
Text apache-2.0
A 2.5B parameter text generation model from openbmb, with 6 MLX builds, from 4-bit to bf16.
- Parameters
- 2.5B From Hugging Face
- Quantisation
- 4-bit MiniCPM5-2B-mlx-4Bit
- Memory needed
- 4 GB Estimate, unified memory
- Download
- 1.4 GB Weights, estimated
- Downloads
- 5.3K This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 6 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 4 GB at 4-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/MiniCPM5-2B-mlx-4Bit --prompt "Hello"MLX builds
6 on mlx-community| MiniCPM5-2B-mlx-4Bit | 4-bit | 1.4 GB | 4 GB | 5.3K |
|---|---|---|---|---|
| MiniCPM5-2B-chat-mlx-4bit | 4-bit | 1.4 GB | 4 GB | 1.1K |
| MiniCPM5-2B-OptiQ-4bit | 4-bit | 1.4 GB | 4 GB | 846 |
| MiniCPM5-2B-8bit | 8-bit | 2.7 GB | 5 GB | 1.8K |
| MiniCPM5-2B-chat-mlx-16bit | 16-bit | 5.0 GB | 8 GB | 438 |
| MiniCPM5-2B-bf16 | bf16 | 5.0 GB | 8 GB | 142 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.