Instructions to use RabiatS/Llama-3.2-3B-Instruct-4bit-Lantern with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RabiatS/Llama-3.2-3B-Instruct-4bit-Lantern 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("RabiatS/Llama-3.2-3B-Instruct-4bit-Lantern")

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 RabiatS/Llama-3.2-3B-Instruct-4bit-Lantern with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "RabiatS/Llama-3.2-3B-Instruct-4bit-Lantern"

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": "RabiatS/Llama-3.2-3B-Instruct-4bit-Lantern"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use RabiatS/Llama-3.2-3B-Instruct-4bit-Lantern with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "RabiatS/Llama-3.2-3B-Instruct-4bit-Lantern"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "RabiatS/Llama-3.2-3B-Instruct-4bit-Lantern"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "RabiatS/Llama-3.2-3B-Instruct-4bit-Lantern",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use RabiatS/Llama-3.2-3B-Instruct-4bit-Lantern 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 "RabiatS/Llama-3.2-3B-Instruct-4bit-Lantern"

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 RabiatS/Llama-3.2-3B-Instruct-4bit-Lantern

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use RabiatS/Llama-3.2-3B-Instruct-4bit-Lantern with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "RabiatS/Llama-3.2-3B-Instruct-4bit-Lantern"

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 "RabiatS/Llama-3.2-3B-Instruct-4bit-Lantern" \
  --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"

Llama 3.2 3B Instruct, 4-bit MLX, for Lantern

Built with Llama

A copy of mlx-community/Llama-3.2-3B-Instruct-4bit, kept here for Lantern, an offline, private AI app for iPhone, iPad and Mac. The model runs entirely on the device: no account, no server, and nothing you type leaves it. The only network use is downloading these files once.

The weights are unchanged from the mlx-community conversion. The original model is meta-llama/Llama-3.2-3B-Instruct.


Parameters	3.2 billion
Precision	4-bit, MLX format
Download	about 1.8 GB
Takes in	text
Runs on	6 GB iPhones with a memory warning, comfortable on 8 GB phones (iPhone 15 Pro, every iPhone 16 and 17) and any Apple silicon Mac.

Good for: Better reasoning and longer answers than the small models.

Use it in Lantern

Lantern already lists this model. To download this copy instead, open Settings, turn on Show advanced options, choose Add a model from Hugging Face and enter RabiatS/Llama-3.2-3B-Instruct-4bit-Lantern. Lantern checks it against your device's memory before anything downloads.

Use it with mlx-lm on a Mac

pip install mlx-lm
mlx_lm.generate --model RabiatS/Llama-3.2-3B-Instruct-4bit-Lantern --prompt "Name two things to pack for a rainy hike."

Licence

Llama 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved. The licence and Meta's Acceptable Use Policy are in LICENSE and USE_POLICY.md in this repository. Use of this model must follow both.

Credit for the model goes to its authors, and for the MLX conversion to mlx-community.

Downloads last month: 48

Safetensors

Model size

3B params

Tensor type

U32

F16

MLX

Hardware compatibility

4-bit

Model tree for RabiatS/Llama-3.2-3B-Instruct-4bit-Lantern

Base model

meta-llama/Llama-3.2-3B-Instruct

Quantized

(548)

this model

Collection including RabiatS/Llama-3.2-3B-Instruct-4bit-Lantern

Lantern: offline private AI

Collection

Models for Lantern, an AI app that runs entirely on your iPhone, iPad or Mac. No account, no server, nothing leaves the device. • 7 items • Updated Sep 28