Instructions to use mlx-community/Ornith-1.0-35B-OptiQ-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/Ornith-1.0-35B-OptiQ-4bit 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/Ornith-1.0-35B-OptiQ-4bit")
config = load_config("mlx-community/Ornith-1.0-35B-OptiQ-4bit")

# 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/Ornith-1.0-35B-OptiQ-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/Ornith-1.0-35B-OptiQ-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/Ornith-1.0-35B-OptiQ-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use mlx-community/Ornith-1.0-35B-OptiQ-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/Ornith-1.0-35B-OptiQ-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/Ornith-1.0-35B-OptiQ-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mlx-community/Ornith-1.0-35B-OptiQ-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/Ornith-1.0-35B-OptiQ-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/Ornith-1.0-35B-OptiQ-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-community/Ornith-1.0-35B-OptiQ-6bit

by ahmedihamdy - opened 17 days ago

Discussion

ahmedihamdy

17 days ago

Hello Folks,

first, many thanks for all the model variety and appreciate the community help.

If anyone has the time to produce a mlx-community/Ornith-1.0-35B-OptiQ-6bit with vision , that would be very helpful.

again thanks a lot for all the support from the community.

codelion

MLX Community org 16 days ago

•

edited 16 days ago

Done: https://huggingface.co/mlx-community/Ornith-1.0-35B-OptiQ-6bit

6/8 mixed precision, 27 GB from a 70.2 GB bf16 base, with the vision tower kept at bf16 in a sidecar. Text and image input were both verified on the finished artifact.

ahmedihamdy

16 days ago

Done: https://huggingface.co/mlx-community/Ornith-1.0-35B-OptiQ-6bit

6/8 mixed precision, 27 GB from a 70.2 GB bf16 base, with the vision tower kept at bf16 in a sidecar. Text and image input were both verified on the finished artifact.

It is a 256-expert MoE, so serve it with SSD expert streaming and it runs in about 7 GB resident:
optiq serve --model mlx-community/Ornith-1.0-35B-OptiQ-6bit --stream-experts
The endpoint takes image content parts directly.

THANKYOUUUUUUUUUU

jorgemunozl

MLX Community org 16 days ago

Thank you! we appreciate quite a lot

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment