Instructions to use divinetribe/gemma-4-31b-it-abliterated-4bit-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use divinetribe/gemma-4-31b-it-abliterated-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("divinetribe/gemma-4-31b-it-abliterated-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 divinetribe/gemma-4-31b-it-abliterated-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 "divinetribe/gemma-4-31b-it-abliterated-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": "divinetribe/gemma-4-31b-it-abliterated-4bit-mlx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use divinetribe/gemma-4-31b-it-abliterated-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 "divinetribe/gemma-4-31b-it-abliterated-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 "divinetribe/gemma-4-31b-it-abliterated-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"

MLX LM

How to use divinetribe/gemma-4-31b-it-abliterated-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 "divinetribe/gemma-4-31b-it-abliterated-4bit-mlx"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "divinetribe/gemma-4-31b-it-abliterated-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": "divinetribe/gemma-4-31b-it-abliterated-4bit-mlx",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use divinetribe/gemma-4-31b-it-abliterated-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 "divinetribe/gemma-4-31b-it-abliterated-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 divinetribe/gemma-4-31b-it-abliterated-4bit-mlx

Run Hermes

hermes

gemma-4-31b-it-abliterated-4bit-mlx

A 4-bit MLX quantization of null-space/gemma-4-31b-it-abliterated, tuned for fast on-device inference on Apple Silicon.

Base model: null-space/gemma-4-31b-it-abliterated (BF16, ~62 GB)
Quantization: 4-bit affine, group size 64
Format: MLX safetensors
Footprint: ~16 GB on disk, runs comfortably on a 32 GB Mac and flies on 64 GB+
Throughput: ~15 tok/s on M4 Max (measured with mlx-lm 0.21+)

Why this exists

The default model in nicedreamzapp/claude-code-local used to point at a mlx-community/... repo that never actually existed. This is the real, working 4-bit quant — drop-in replacement.

Usage

from mlx_lm import load, generate

model, tokenizer = load("divinetribe/gemma-4-31b-it-abliterated-4bit-mlx")
print(generate(model, tokenizer, prompt="Hello", max_tokens=200))

Or via the launcher / setup script in claude-code-local:

MLX_MODEL=divinetribe/gemma-4-31b-it-abliterated-4bit-mlx \
  bash scripts/start-mlx-server.sh

Abliteration

Refusal-direction projection per Arditi et al. (2024). Use responsibly — you are now the moderator.

About the author

This model was built by Matt Macosko (@nicedreamzapp) for the claude-code-local stack — run Claude Code 100% on-device with local AI on Apple Silicon (⭐ 2,664 on GitHub).