Instructions to use majentik/gemma-4-26B-A4B-it-RotorQuant-MLX-2bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use majentik/gemma-4-26B-A4B-it-RotorQuant-MLX-2bit 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("majentik/gemma-4-26B-A4B-it-RotorQuant-MLX-2bit")
config = load_config("majentik/gemma-4-26B-A4B-it-RotorQuant-MLX-2bit")

# 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 majentik/gemma-4-26B-A4B-it-RotorQuant-MLX-2bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "majentik/gemma-4-26B-A4B-it-RotorQuant-MLX-2bit"

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": "majentik/gemma-4-26B-A4B-it-RotorQuant-MLX-2bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use majentik/gemma-4-26B-A4B-it-RotorQuant-MLX-2bit 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 "majentik/gemma-4-26B-A4B-it-RotorQuant-MLX-2bit"

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 majentik/gemma-4-26B-A4B-it-RotorQuant-MLX-2bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use majentik/gemma-4-26B-A4B-it-RotorQuant-MLX-2bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "majentik/gemma-4-26B-A4B-it-RotorQuant-MLX-2bit"

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 "majentik/gemma-4-26B-A4B-it-RotorQuant-MLX-2bit" \
  --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"

Unsupported safetensor format: null"

by dextml - opened 26 days ago

Discussion

dextml

26 days ago

Not loading in LM studio

majentik

Owner 10 days ago

Thanks for the report — you found a real bug, and it's now fixed.

Root cause: the top-level quantization.bits field in config.json said 4 while the tensors are actually 2-bit packed (the sibling quantization_config correctly said 2). Loaders that trust quantization.bits (including LM Studio's MLX engine) tried to unpack the weights with the wrong bit-width and failed with Unsupported safetensor format: null.

Fix: config.json in this repo has been corrected (quantization.bits: 2, per-layer overrides unchanged). We audited all 273 quantized configs in the org and fixed the same mismatch in all 22 affected 2-bit repos.

Please re-download the model (or just refresh config.json) and it should load. Reopen if you still hit issues.

majentik

Owner 10 days ago

Fixed — config metadata corrected across all affected repos.

majentik changed discussion status to closed 10 days ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment