Instructions to use lee-loo/MiniCPM5-2B-MLX-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lee-loo/MiniCPM5-2B-MLX-bf16 with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("lee-loo/MiniCPM5-2B-MLX-bf16")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use lee-loo/MiniCPM5-2B-MLX-bf16 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "lee-loo/MiniCPM5-2B-MLX-bf16"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "lee-loo/MiniCPM5-2B-MLX-bf16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use lee-loo/MiniCPM5-2B-MLX-bf16 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "lee-loo/MiniCPM5-2B-MLX-bf16"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "lee-loo/MiniCPM5-2B-MLX-bf16"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "lee-loo/MiniCPM5-2B-MLX-bf16",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use lee-loo/MiniCPM5-2B-MLX-bf16 with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "lee-loo/MiniCPM5-2B-MLX-bf16"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default lee-loo/MiniCPM5-2B-MLX-bf16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use lee-loo/MiniCPM5-2B-MLX-bf16 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "lee-loo/MiniCPM5-2B-MLX-bf16"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "lee-loo/MiniCPM5-2B-MLX-bf16" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

MiniCPM5-2B MLX BF16

BF16 MLX conversion of openbmb/MiniCPM5-2B.

This conversion preserves BF16 precision and performs no quantization.

Why?

At the time the official MLX version was only 4 bit quant.

Conversion

Converted from the official OpenBMB checkpoint using mlx-lm 0.31.3:

mlx_lm.convert \
  --hf-path openbmb/MiniCPM5-2B \
  --mlx-path MiniCPM5-2B-MLX-bf16 \
  --dtype bfloat16

Precision verification

All tensors in the converted safetensors files were verified as BF16:

Counter({'mlx.core.bfloat16': 381})

Tested hardware

Apple M4 Max with 128 GB unified memory.

Observed with mlx_lm.generate:

Peak memory: approximately 5.1 GB
Decode: approximately 96 tokens/sec
Prefill: approximately 2300 tokens/sec on a short test
MLX-LM: 0.31.3

Performance varies with prompt length, generation settings, and hardware.

Usage

mlx_lm.generate \
  --model MiniCPM5-2B-MLX-bf16 \
  --prompt "explain in two sentences quantum physics" \
  --max-tokens 512

MiniCPM5-2B supports thinking/reasoning output. For interactive or low-latency workloads, generation settings should be chosen according to the intended use case.

Original model

Architecture, training details, benchmarks, limitations, license information, and citation are available from the original model:

openbmb/MiniCPM5-2B

https://huggingface.co/openbmb/MiniCPM5-2B

Conversion provenance

OpenBMB official MiniCPM5-2B BF16 weights => mlx-lm 0.31.3 => MLX BF16 weights no quantization

Downloads last month: 15

Safetensors

Model size

3B params

Tensor type

BF16

MLX

Hardware compatibility

Quantized

Model tree for lee-loo/MiniCPM5-2B-MLX-bf16

Base model

openbmb/MiniCPM5-2B

Finetuned

(9)

this model