Instructions to use bearzi/gemma-4-31B-it-JANG_2M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bearzi/gemma-4-31B-it-JANG_2M 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("bearzi/gemma-4-31B-it-JANG_2M")

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 bearzi/gemma-4-31B-it-JANG_2M with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "bearzi/gemma-4-31B-it-JANG_2M"

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": "bearzi/gemma-4-31B-it-JANG_2M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use bearzi/gemma-4-31B-it-JANG_2M 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 "bearzi/gemma-4-31B-it-JANG_2M"

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 bearzi/gemma-4-31B-it-JANG_2M

Run Hermes

hermes

MLX LM

How to use bearzi/gemma-4-31B-it-JANG_2M with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "bearzi/gemma-4-31B-it-JANG_2M"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "bearzi/gemma-4-31B-it-JANG_2M"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "bearzi/gemma-4-31B-it-JANG_2M",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

⚠️ Low-bit quality warning

This is an aggressive quantization (2-bit average). At this compression level, output quality degrades noticeably — responses may start coherent but degenerate into repetition or garbage tokens toward the end of longer generations. This is expected behavior for 2-bit quantization on this architecture.

Recommended for: experimentation, quick testing, extreme memory constraints. Not recommended for: production use, long-form generation, coding tasks.

For reliable output quality, use JANG_4M or higher profiles from this collection.

gemma-4-31B-it-JANG_2M

JANG adaptive mixed-precision MLX quantization produced via vmlx / jang-tools.

Quantization: 3.75b avg, profile JANG_2M, method mse-all, calibration activations
Profile: JANG_2M
Format: JANG v2 MLX safetensors
Compatible with: vmlx, MLX Studio, oMLX (with JANG patch)

Usage

vmlx (recommended)

pip install 'vmlx[jang]'
vmlx serve bearzi/gemma-4-31B-it-JANG_2M

Python

from jang_tools.loader import load_jang_model
from mlx_lm import generate

model, tokenizer = load_jang_model("bearzi/gemma-4-31B-it-JANG_2M")
messages = [{"role": "user", "content": "Hello"}]
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
print(generate(model, tokenizer, prompt=prompt, max_tokens=512, verbose=True))

About JANG

JANG (Jang Adaptive N-bit Grading) assigns different bit widths to different layer types — attention layers get more bits, MLP/expert layers compress harder. This preserves model coherence at aggressive compression levels where uniform quantization breaks down.

See JANG documentation and scores at jangq.ai.

Comparative benchmarks and feedback welcome — please open a discussion.