Instructions to use nuroai/eliot-9b-mlx-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nuroai/eliot-9b-mlx-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("nuroai/eliot-9b-mlx-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 nuroai/eliot-9b-mlx-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 "nuroai/eliot-9b-mlx-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": "nuroai/eliot-9b-mlx-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use nuroai/eliot-9b-mlx-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 "nuroai/eliot-9b-mlx-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 nuroai/eliot-9b-mlx-4bit

Run Hermes

hermes

OpenClaw new

How to use nuroai/eliot-9b-mlx-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 "nuroai/eliot-9b-mlx-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 "nuroai/eliot-9b-mlx-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 nuroai/eliot-9b-mlx-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 "nuroai/eliot-9b-mlx-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "nuroai/eliot-9b-mlx-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "nuroai/eliot-9b-mlx-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Eliot 9B MLX 4-bit

This is the Apple Silicon optimized MLX 4-bit build of Eliot 9B.

For the canonical full BF16 checkpoint, use nuroai/eliot-9b.

Run On Apple Silicon

pip install mlx-lm
mlx_lm.server --model nuroai/eliot-9b-mlx-4bit --port 8081 --host localhost

About Eliot

Eliot is a 9B Apple-platform agent model fine-tuned from Qwen/Qwen3.5-9B to operate a Mac through a guarded macOS Accessibility-tree harness. It emits structured tool calls for actions such as clicking, typing, opening apps, reading UI state, asking the user, and finishing tasks.

This MLX artifact is intended for resident local Mac use. The model is not the safety boundary; destructive, external, credential, payment, network, file-write, send, delete, and shell actions should be intercepted by a deterministic harness before execution.

Eliot is an independent project by Nuro AI Labs. It is designed for Apple-platform and macOS workflows, but it is not created by, endorsed by, sponsored by, or affiliated with Apple Inc.

Downloads last month: 127

Safetensors

Model size

1B params

Tensor type

BF16

U32

F32

MLX

Hardware compatibility

4-bit

Model tree for nuroai/eliot-9b-mlx-4bit

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Quantized

(341)

this model