Instructions to use abenzerps/Clef-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abenzerps/Clef-MLX 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("abenzerps/Clef-MLX")
config = load_config("abenzerps/Clef-MLX")

# 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 abenzerps/Clef-MLX with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "abenzerps/Clef-MLX"

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": "abenzerps/Clef-MLX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use abenzerps/Clef-MLX 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 "abenzerps/Clef-MLX"

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 abenzerps/Clef-MLX

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use abenzerps/Clef-MLX with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "abenzerps/Clef-MLX"

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 "abenzerps/Clef-MLX" \
  --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"

Clef-MLX / Clef-MLX-4bit /README.md

abenzerps

Initial Commit: Add MLX quantizations for Cloudflare/clef

d81b074 25 days ago

preview code

Raw History Blame Contribute Delete

815 Bytes

---
base_model: Cloudflare/clef
library_name: mlx
pipeline_tag: image-text-to-text
tags:
- mlx
- multimodal
- decision-model
- 4bit
license: apache-2.0
---
# clef-mlx-4bit

This model is a 4-bit quantized version of [Cloudflare/clef](https://huggingface.co/Cloudflare/clef) using the [MLX](https://github.com/ml-explore/mlx) framework.

## Model Details
- **Base Model:** [Cloudflare/clef](https://huggingface.co/Cloudflare/clef)
- **Architecture:**  + Joint Schema Head
- **Quantization:** 4-bit affine (group size: 64)
- **Effective Bits Per Weight:** 4.695 bpw
- **Model Size:** ~16 GB
- **License:** Apache-2.0

## Files Included
- Quantized backbone weights (, )
- Joint Schema Head weights (, )
- Model execution code ()
- Processor & Tokenizer configs (, , , )
- Model Configuration (, )

## Usage with MLX

	---
	base_model: Cloudflare/clef
	library_name: mlx
	pipeline_tag: image-text-to-text
	tags:
	- mlx
	- multimodal
	- decision-model
	- 4bit
	license: apache-2.0
	---

	# clef-mlx-4bit

	This model is a 4-bit quantized version of [Cloudflare/clef](https://huggingface.co/Cloudflare/clef) using the [MLX](https://github.com/ml-explore/mlx) framework.

	## Model Details
	- Base Model: [Cloudflare/clef](https://huggingface.co/Cloudflare/clef)
	- Architecture: + Joint Schema Head
	- Quantization: 4-bit affine (group size: 64)
	- Effective Bits Per Weight: 4.695 bpw
	- Model Size: ~16 GB
	- License: Apache-2.0

	## Files Included
	- Quantized backbone weights (, )
	- Joint Schema Head weights (, )
	- Model execution code ()
	- Processor & Tokenizer configs (, , , )
	- Model Configuration (, )

	## Usage with MLX