Instructions to use Vontra/GLM-5.3-Flash-MLX-oQ2-MTP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Vontra/GLM-5.3-Flash-MLX-oQ2-MTP 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("Vontra/GLM-5.3-Flash-MLX-oQ2-MTP")
config = load_config("Vontra/GLM-5.3-Flash-MLX-oQ2-MTP")

# 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 Vontra/GLM-5.3-Flash-MLX-oQ2-MTP with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Vontra/GLM-5.3-Flash-MLX-oQ2-MTP"

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": "Vontra/GLM-5.3-Flash-MLX-oQ2-MTP"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use Vontra/GLM-5.3-Flash-MLX-oQ2-MTP 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 "Vontra/GLM-5.3-Flash-MLX-oQ2-MTP"

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 Vontra/GLM-5.3-Flash-MLX-oQ2-MTP

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Vontra/GLM-5.3-Flash-MLX-oQ2-MTP with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Vontra/GLM-5.3-Flash-MLX-oQ2-MTP"

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 "Vontra/GLM-5.3-Flash-MLX-oQ2-MTP" \
  --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"

Possible to get a Non-MTP for size reduction or REAP?

by ch33ky - opened 2 days ago

Discussion

ch33ky

2 days ago

M5 Max 128GB user here - thank you so much for these quants!

Any chance of a non mtp or slightly REAP’d variation? Would fit nicely on 128GB

ashxhart

Vontra org 1 day ago

Thanks, glad the quants are useful! There are already some REAP50 variants available, so I’m looking at whether a non-MTP MLX build or a lighter MLX-specific REAP version would be worthwhile for 128GB Macs; I’ll update the discussion once I’ve tested the options.

ch33ky

about 15 hours ago

Is it possible to do an oQ2e with no mtp and text only checked? Based on my oMLX projection it says 98.6 GB which would fit perfectly on an M5 Max 128GB.

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