Instructions to use bearzi/gemma-4-31B-it-JANG_1L with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bearzi/gemma-4-31B-it-JANG_1L 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_1L")

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 bearzi/gemma-4-31B-it-JANG_1L 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_1L"

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": "bearzi/gemma-4-31B-it-JANG_1L"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use bearzi/gemma-4-31B-it-JANG_1L 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_1L"

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_1L"
# 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_1L",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use bearzi/gemma-4-31B-it-JANG_1L 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_1L"

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_1L

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use bearzi/gemma-4-31B-it-JANG_1L with OpenClaw:

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_1L"

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 "bearzi/gemma-4-31B-it-JANG_1L" \
  --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-4-31B-it-JANG_1L / README.md

bearzi

Update README.md

d9b03ce verified 5 months ago

preview code

Raw

History Blame Contribute Delete

2.1 kB

	---
	base_model: google/gemma-4-31B-it
	library_name: mlx
	pipeline_tag: text-generation
	license: apache-2.0
	tags:
	- mlx
	- jang
	- jang-quantized
	- JANG_1L
	- mixed-precision
	- apple-silicon
	---

	## ⚠️ 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_1L

	JANG adaptive mixed-precision MLX quantization produced via [vmlx / jang-tools](https://github.com/jjang-ai/jangq).

	- Quantization: 3.93b avg, profile JANG_1L, method mse-all, calibration activations
	- Profile: JANG_1L
	- Format: JANG v2 MLX safetensors
	- Compatible with: vmlx, MLX Studio, oMLX (with JANG patch)

	## Usage

	### vmlx (recommended)

	```bash
	pip install 'vmlx[jang]'
	vmlx serve bearzi/gemma-4-31B-it-JANG_1L
	```

	### Python

	```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_1L")
	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](https://github.com/jjang-ai/jangq) and scores at [jangq.ai](https://jangq.ai).

	Comparative benchmarks and feedback welcome — please open a discussion.