Instructions to use mlx-community/Mellum2-12B-A2.5B-Instruct-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/Mellum2-12B-A2.5B-Instruct-4bit 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("mlx-community/Mellum2-12B-A2.5B-Instruct-4bit")

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 mlx-community/Mellum2-12B-A2.5B-Instruct-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/Mellum2-12B-A2.5B-Instruct-4bit"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "mlx-community/Mellum2-12B-A2.5B-Instruct-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use mlx-community/Mellum2-12B-A2.5B-Instruct-4bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/Mellum2-12B-A2.5B-Instruct-4bit"

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 "mlx-community/Mellum2-12B-A2.5B-Instruct-4bit" \
  --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"

MLX LM

How to use mlx-community/Mellum2-12B-A2.5B-Instruct-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "mlx-community/Mellum2-12B-A2.5B-Instruct-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mlx-community/Mellum2-12B-A2.5B-Instruct-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "mlx-community/Mellum2-12B-A2.5B-Instruct-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use mlx-community/Mellum2-12B-A2.5B-Instruct-4bit 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 "mlx-community/Mellum2-12B-A2.5B-Instruct-4bit"

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 mlx-community/Mellum2-12B-A2.5B-Instruct-4bit

Run Hermes

hermes

Atomic Chat

Mellum2 12B A2.5B Instruct - 4-bit MLX

This is a 4-bit affine MLX quantization of JetBrains/Mellum2-12B-A2.5B-Instruct.

Mellum2 Instruct is a Mixture-of-Experts assistant model with 64 experts and 8 active experts per token. It supports a 131,072-token context window and is optimized for direct instruction following.

Conversion details

Source: JetBrains/Mellum2-12B-A2.5B-Instruct
Format: MLX safetensors
Quantization: affine, 4 bits, group size 64
License: Apache-2.0
EOS token: <|im_end|> (token ID 28)

The upstream config.json and generation_config.json identify token ID 0 as the EOS token, while the tokenizer identifies <|im_end|> (ID 28) as EOS. This conversion uses token ID 28 so MLX generation stops at the end of the assistant turn.

Usage

pip install -U mlx-lm

mlx_lm.chat \
  --model mlx-community/Mellum2-12B-A2.5B-Instruct-4bit \
  --max-tokens 8192 \
  --temp 0.6 \
  --top-p 0.95

Model provenance

For the original model card, training details, benchmark results, and usage guidance, see the upstream JetBrains checkpoint.

Downloads last month: 14

Safetensors

Model size

2B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for mlx-community/Mellum2-12B-A2.5B-Instruct-4bit

Base model

JetBrains/Mellum2-12B-A2.5B-Instruct

Quantized

(23)

this model