Instructions to use dealignai/Gemma-4-31B-JANG_4M-CRACK with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dealignai/Gemma-4-31B-JANG_4M-CRACK with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("dealignai/Gemma-4-31B-JANG_4M-CRACK")
config = load_config("dealignai/Gemma-4-31B-JANG_4M-CRACK")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use dealignai/Gemma-4-31B-JANG_4M-CRACK with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "dealignai/Gemma-4-31B-JANG_4M-CRACK"

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": "dealignai/Gemma-4-31B-JANG_4M-CRACK"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use dealignai/Gemma-4-31B-JANG_4M-CRACK 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 "dealignai/Gemma-4-31B-JANG_4M-CRACK"

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 dealignai/Gemma-4-31B-JANG_4M-CRACK

Run Hermes

hermes

OpenClaw new

How to use dealignai/Gemma-4-31B-JANG_4M-CRACK with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "dealignai/Gemma-4-31B-JANG_4M-CRACK"

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 "dealignai/Gemma-4-31B-JANG_4M-CRACK" \
  --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"

New discussion

Resources

View closed (3)

Add base_model metadata (google/gemma-4-31B-it)

#27 opened about 2 months ago by

victor

is there any research efforts to provide executive "summaries" or event topics / titles that drift?

#26 opened about 2 months ago by

johndpope

Fix loading in LM Studio / mlx-llm: quant map keys + vision weights

#25 opened 3 months ago by

IsaacLiu

Update README.md

#23 opened 3 months ago by

jone455

Your JANG quantization and CRACK surgery — the math behind why they work

🔥 1

#22 opened 3 months ago by

wehe1pwe

Why does my “jailbroken” Hugging Face LLM still refuse answers in VMLX?

❤️ 1

#21 opened 3 months ago by

Gifsaint

can't loan model

#20 opened 3 months ago by

thomas08

Request: DOI

#19 opened 3 months ago by

qiuxinai808

c:\gemma4

#18 opened 3 months ago by

ricolau2012

dealignai/Gemma-4-31B-JANG_4M-CRACK

#17 opened 3 months ago by

Asoina

GEMMA4

#16 opened 3 months ago by

jkik

dealignai/Gemma-4-31B-JANG_4M-CRACK

#15 opened 3 months ago by

legalcase

Upload folder using huggingface_hub

#14 opened 3 months ago by

Osaurus-AI

Upload README.md with huggingface_hub

#13 opened 3 months ago by

Osaurus-AI

its not uncensored

#12 opened 4 months ago by

agapes

Disappointed: Vision feature is unusable (Outputs infinite <pad> tokens)

😔 2

#11 opened 4 months ago by

ratalai

Is it possible to make a NVFP4 version?

#10 opened 4 months ago by

DanielLien

Cann't load it in LMStudio

👍 1

#9 opened 4 months ago by

TheXAbove

LM Studio Cannot Download dealignai/Gemma-4-31B-JANG_4M-CRACK on Debian 12

#7 opened 4 months ago by

hereww

Models running on non-Mac systems are now supported as soon as possible

🚀 2

#6 opened 4 months ago by

XiaoZaiyi

Run with mlx_lm on macos if encountered error with LLM Studio

👍 1

#5 opened 4 months ago by

stiron9

Refusal rate very high on questions beyond cybersecurity

#4 opened 4 months ago by

Zayaan

Will this work in a Window's-based ComfyUI install in the Text_encoder model folder ?

#2 opened 4 months ago by

StevieTee

Can you please release GGUF versions ?

#1 opened 4 months ago by

PaPaai99