Instructions to use mlx-community/AREX-2-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/AREX-2-8bit with MLX:

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

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("mlx-community/AREX-2-8bit")
config = load_config("mlx-community/AREX-2-8bit")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use mlx-community/AREX-2-8bit 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/AREX-2-8bit"

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": "mlx-community/AREX-2-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use mlx-community/AREX-2-8bit 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/AREX-2-8bit"

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/AREX-2-8bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mlx-community/AREX-2-8bit 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/AREX-2-8bit"

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/AREX-2-8bit" \
  --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"

muscleotter commited on 5 days ago

Commit

369a0ff

verified ·

1 Parent(s): 62b19d5

Link the test scripts on GitHub

Browse files

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -127,7 +127,8 @@ use `http://localhost:1234/v1` with this model, including tool calls and images.
 - **It can run more than twice as fast with a speed helper.** The DFlash2 helper for Qwen3.8-27B ([incoai/Qwen3.8-27B-DFlash2](https://huggingface.co/incoai/Qwen3.8-27B-DFlash2)) works with AREX-2 as it is. In mlx-dspark it took the 8-bit from 8 to 19 tokens per second.
 - **Every size passed** a four-step tool task, a 32,000-token recall test, 11 image questions, and loading in LM Studio.
-The numbers are below. The scripts and raw results are in the [`tests`](https://huggingface.co/mlx-community/AREX-2-8bit/tree/main/tests) folder.
 <details>
 <summary>AREX-2 compared with plain Qwen3.8-27B</summary>

 - **It can run more than twice as fast with a speed helper.** The DFlash2 helper for Qwen3.8-27B ([incoai/Qwen3.8-27B-DFlash2](https://huggingface.co/incoai/Qwen3.8-27B-DFlash2)) works with AREX-2 as it is. In mlx-dspark it took the 8-bit from 8 to 19 tokens per second.
 - **Every size passed** a four-step tool task, a 32,000-token recall test, 11 image questions, and loading in LM Studio.
+The numbers are below. The scripts and raw results are in the [`tests`](https://huggingface.co/mlx-community/AREX-2-8bit/tree/main/tests) folder,
+and on GitHub at [MuscleOtter/arex-2-mlx-tests](https://github.com/MuscleOtter/arex-2-mlx-tests).
 <details>
 <summary>AREX-2 compared with plain Qwen3.8-27B</summary>