Instructions to use DreamFoundries/gemma-4-12B-it-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DreamFoundries/gemma-4-12B-it-6bit 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("DreamFoundries/gemma-4-12B-it-6bit")

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 DreamFoundries/gemma-4-12B-it-6bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "DreamFoundries/gemma-4-12B-it-6bit"

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": "DreamFoundries/gemma-4-12B-it-6bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use DreamFoundries/gemma-4-12B-it-6bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "DreamFoundries/gemma-4-12B-it-6bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "DreamFoundries/gemma-4-12B-it-6bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "DreamFoundries/gemma-4-12B-it-6bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use DreamFoundries/gemma-4-12B-it-6bit 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 "DreamFoundries/gemma-4-12B-it-6bit"

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 DreamFoundries/gemma-4-12B-it-6bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use DreamFoundries/gemma-4-12B-it-6bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "DreamFoundries/gemma-4-12B-it-6bit"

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 "DreamFoundries/gemma-4-12B-it-6bit" \
  --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"

gemma-4-12B-it-6bit

File size: 1,839 Bytes

---
library_name: mlx
base_model: google/gemma-4-12B-it
license: apache-2.0
pipeline_tag: text-generation
tags:
- mlx
- mlx-lm
- quantized
- 6-bit
- base_model:google/gemma-4-12B-it
---

[![Open in MLXHub](https://mlxhub.app/assets/badge-open-in-mlxhub.svg)](https://mlxhub.app/open-model?repo=DreamFoundries/gemma-4-12B-it-6bit)

# gemma-4-12B-it MLX 6-bit

This repository contains an MLX-LM conversion of [google/gemma-4-12B-it](https://huggingface.co/google/gemma-4-12B-it).

## Conversion Details

- Original model: `google/gemma-4-12B-it`
- Model family: Gemma4
- Source model type: `gemma4_unified`
- Model size: 11,959,730,224 parameters
- Quantization: MLX-LM affine quantization
- Bits: 6-bit
- Group size: 64
- Local MLX folder size at upload time: 9.04 GiB
- Local safetensors weight size at upload time: 9.01 GiB

This Gemma conversion follows the MLX-LM Gemma 4 shared-KV topology and uses non-strict checkpoint loading so extra HF tensors outside that topology are discarded during conversion.

The temporary conversion config remapped `gemma4_unified` to `gemma4` because this mlx-lm build exposes that Gemma 4 implementation.

## Usage

```bash
mlx_lm.generate --model DreamFoundries/gemma-4-12B-it-6bit --prompt "Hello" --max-tokens 64
```

## Benchmarks

No comparative benchmarks have been run yet. The repository does not currently provide quality, speed, memory, or benchmark comparisons against the original weights or other quantizations.

## License

This is a converted/quantized derivative of the original model. Please refer to the original model repository for the upstream license and usage terms: https://huggingface.co/google/gemma-4-12B-it

---

[![Download MLXHub](https://mlxhub.app/assets/badge-download-mlxhub.svg)](https://apps.apple.com/app/apple-store/id6766485144?pt=121945436&ct=HuggingFace&mt=8)