Instructions to use modelcaddy/gemma-4-12b-it-qat-4bit-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use modelcaddy/gemma-4-12b-it-qat-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("modelcaddy/gemma-4-12b-it-qat-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 Settings
LM Studio

How to use modelcaddy/gemma-4-12b-it-qat-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 "modelcaddy/gemma-4-12b-it-qat-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": "modelcaddy/gemma-4-12b-it-qat-4bit-mlx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use modelcaddy/gemma-4-12b-it-qat-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 "modelcaddy/gemma-4-12b-it-qat-4bit-mlx"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "modelcaddy/gemma-4-12b-it-qat-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": "modelcaddy/gemma-4-12b-it-qat-4bit-mlx",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use modelcaddy/gemma-4-12b-it-qat-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 "modelcaddy/gemma-4-12b-it-qat-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 modelcaddy/gemma-4-12b-it-qat-4bit-mlx

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use modelcaddy/gemma-4-12b-it-qat-4bit-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 "modelcaddy/gemma-4-12b-it-qat-4bit-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 "modelcaddy/gemma-4-12b-it-qat-4bit-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"

gemma-4-12b-it-qat-4bit-mlx

Uniform 4-bit MLX conversion of Google's QAT (quantization-aware trained) Gemma 4 12B instruction-tuned checkpoint. Built and used by ModelCaddy as the on-device generation model for its Pro tier (local conversation extraction and memory synthesis on Apple Silicon).

Provenance

Source: google/gemma-4-12B-it-qat-q4_0-unquantized — the bf16 QAT weights Google publishes for downstream quantization.
Conversion: mlx_vlm.convert -q --q-bits 4 --q-group-size 64 (mlx-vlm 0.6.13, mlx 0.32.0).
Result: ~6.3 GB on disk, 4.51 effective bits per weight, uniform 4-bit affine quantization (group size 64). No layers held back at higher precision — the QAT training is what preserves quality at uniform 4-bit.

Why the Hub shows "~2B params" for a 12B model

The Hub counts stored safetensors elements. MLX packs eight 4-bit weights into each stored U32, so the counter sees 1.49B U32 containers + 0.38B BF16 quantization scales ≈ 1.9B stored elements and rounds to "2B". Unpacked, the model is 12.33B parameters (1.49B × 8 + 0.38B) — the full Gemma 4 12B. Cross-check: 12.33B × 4.51 bits ÷ 8 ≈ 6.9 GB, matching the shard sizes. Every 4-bit MLX repo on the Hub under-displays the same way.

Requirements

Apple Silicon and mlx-vlm >= 0.6.x (the gemma4_unified architecture is not supported by mlx-vlm 0.5.x).

pip install -U mlx-vlm
python -m mlx_vlm generate --model modelcaddy/gemma-4-12b-it-qat-4bit-mlx \
  --prompt "Summarize: ..." --max-tokens 256

License

Gemma is provided under and subject to the Gemma Terms of Use. This repository redistributes a quantized derivative of Google's Gemma 4 weights; use is governed by those terms and the Gemma Prohibited Use Policy.