---
base_model: openbmb/MiniCPM5-2B
base_model_relation: quantized
license: apache-2.0
language:
  - en
  - zh
pipeline_tag: text-generation
library_name: mlx
tags:
  - mlx
  - mlx-lm
  - 6-bit
  - minicpm5
  - long-context
  - 131k-context
  - dense
  - tool-calling
---

# MiniCPM5-2B MLX - 6-bit

MLX 6-bit conversion of [OpenBMB/MiniCPM5-2B](https://huggingface.co/openbmb/MiniCPM5-2B), a 2B dense Llama-based model for local deployment, coding, reasoning, long-context work, and tool use. The source checkpoint supports a native context length of **131,072 tokens (128K)**.

## Benchmarks

![MiniCPM5-2B evaluation results](assets/minicpm5-benchmark.png)

![MiniCPM5-2B capability radar](assets/minicpm5-benchmark2.png)

*Benchmark results reported by OpenBMB for the original MiniCPM5-2B checkpoint.*

## Release

| Format | Quantization | Size |
| --- | --- | ---: |
| MLX safetensors | Affine 6-bit, group size 64 | 2.0 GB |

The model is text-only. No vision projector or MTP files are included.

## Usage

```bash
pip install -U mlx-lm
mlx_lm.generate \
  --model . \
  --prompt "Explain why reproducible builds matter." \
  --max-tokens 512
```

## Source

- Model: [OpenBMB/MiniCPM5-2B](https://huggingface.co/openbmb/MiniCPM5-2B)
- Source revision: [3497c460c89e00520c3cfa2e73f49ab7647f1177](https://huggingface.co/openbmb/MiniCPM5-2B/tree/3497c460c89e00520c3cfa2e73f49ab7647f1177)
- License: [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0)
- Checksums: [SHA256SUMS.txt](SHA256SUMS.txt)