Instructions to use samuelfaj/distill-1.7B-4bit-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use samuelfaj/distill-1.7B-4bit-MLX 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("samuelfaj/distill-1.7B-4bit-MLX")

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
LM Studio

Pi new

How to use samuelfaj/distill-1.7B-4bit-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 "samuelfaj/distill-1.7B-4bit-MLX"

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": "samuelfaj/distill-1.7B-4bit-MLX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use samuelfaj/distill-1.7B-4bit-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 "samuelfaj/distill-1.7B-4bit-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 samuelfaj/distill-1.7B-4bit-MLX

Run Hermes

hermes

MLX LM

How to use samuelfaj/distill-1.7B-4bit-MLX with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "samuelfaj/distill-1.7B-4bit-MLX"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "samuelfaj/distill-1.7B-4bit-MLX"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "samuelfaj/distill-1.7B-4bit-MLX",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

distill-1.7B-4bit-MLX / README.md

samuelfaj

Upload README.md with huggingface_hub

af905e6 verified 9 days ago

preview code

raw

history blame contribute delete

673 Bytes

	---
	license: apache-2.0
	tags:
	- mlx
	- distill
	- cli
	- code
	- qwen
	- quantized
	- expert-model
	- domain-specific
	pipeline_tag: text-generation
	base_model: samuelfaj/distill-1.7B-MLX
	---

	# distill-1.7B-4bit-MLX

	4-bit quantized version of [distill-1.7B](https://huggingface.co/samuelfaj/distill-1.7B-MLX) — an Expert Language Model for CLI output compression. Zero accuracy loss vs fp16.

	\| Format \| Size \| Accuracy \|
	\|--------\|------\|----------\|
	\| fp16 \| 3.2 GB \| 95% \|
	\| 4-bit \| 1.0 GB \| 95% \|

	Built for [distill](https://github.com/samuelfaj/distill). [Full collection](https://huggingface.co/collections/samuelfaj/distill-6a0606f9b131c289025659fc)