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

Libraries

How to use PollardWeights/MiniCPM5-2B-Pollard-MLX 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("PollardWeights/MiniCPM5-2B-Pollard-MLX")

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 PollardWeights/MiniCPM5-2B-Pollard-MLX with Pi:

Start the MLX server

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

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": "PollardWeights/MiniCPM5-2B-Pollard-MLX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use PollardWeights/MiniCPM5-2B-Pollard-MLX with MLX LM:

Generate or start a chat session

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

Run an OpenAI-compatible server

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

Hermes Agent

How to use PollardWeights/MiniCPM5-2B-Pollard-MLX 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 "PollardWeights/MiniCPM5-2B-Pollard-MLX"

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 PollardWeights/MiniCPM5-2B-Pollard-MLX

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use PollardWeights/MiniCPM5-2B-Pollard-MLX with OpenClaw:

Start the MLX server

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

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 "PollardWeights/MiniCPM5-2B-Pollard-MLX" \
  --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 — Pollard

Pollard shrank this model for Apple Silicon: 5.04 GB (f16) → 1.71 GB — 66% smaller, 3.0× down.

The smallest rung here; larger, higher-fidelity rungs are listed below.

Pollard builds of openbmb/MiniCPM5-2B made with Pollard Weights — a ladder of measured-allocation quants (bits placed by per-layer sensitivity, not a uniform crush).

Model details


Parameter count	~2.5B
Architecture	`llama`
Input support	text
imatrix	no
Perplexity measured	yes — table below

Which file should I choose?

Every rung is the same weights, sized to a different RAM budget by the measured allocation. Pick the largest one that fits your machine with room for context:

~5 GB RAM / VRAM → q8/model.safetensors (2.67 GB).
~4 GB RAM / VRAM → model.safetensors (2.04 GB).
~4 GB RAM / VRAM → q4/model.safetensors (1.71 GB).

Available files

file	PPL	size	Mean KLD	notes
`q4/model.safetensors`	—	1.71 GB	—	q4/model.safetensors
`model.safetensors`	—	2.04 GB	—	model.safetensors
`q8/model.safetensors`	—	2.67 GB	—	q8/model.safetensors

Available rungs

rung	bpw	size	notes	path
q8	8.50	2.5 GB	near-lossless	`q8/`
mix (recommended)	6.48	1.9 GB	measured 4/8 mixed-precision	repo root
q4	5.43	1.6 GB	smallest	`q4/`

PPL / Mean-KLD benchmarking pending — sizes and allocation are final.

Download a specific file

pip install -U "huggingface_hub[cli]"
hf download PollardWeights/MiniCPM5-2B-Pollard-MLX \
  --include "q4/model.safetensors" --local-dir ./

How to run

mlx_lm.generate --model PollardWeights/MiniCPM5-2B-Pollard-MLX --prompt "Hello"

Errata

Measured allocation places bits by per-layer sensitivity under a size budget.
Single machine; replication invited.

Credits & license

Base model: openbmb/MiniCPM5-2B
Quantization tooling: llama.cpp (ggml-org)
Method + tooling: Pollard Weights — measure first, no claim before a number.
License: apache-2.0, inherited from the base model.

Built with Pollard Weights — frontier models, small hardware, no compromise.

Downloads last month: 687

Safetensors

Model size

3B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit

Model tree for PollardWeights/MiniCPM5-2B-Pollard-MLX

Base model

openbmb/MiniCPM5-2B

Quantized

(69)

this model

PollardWeights
/

MiniCPM5-2B-Pollard-MLX

MiniCPM5-2B-MLX — Pollard

Pollard shrank this model for Apple Silicon: 5.04 GB (f16) → 1.71 GB — 66% smaller, 3.0× down.

Model details

Which file should I choose?

Available files

Available rungs

Download a specific file

How to run

Errata

Credits & license

Model tree for PollardWeights/MiniCPM5-2B-Pollard-MLX