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

# 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-4bit 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-4bit"

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-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

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

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-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

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

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-4bit" \
  --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"

is there another quantised varint to be posted for other than MLX

by anvirus - opened Apr 13

Discussion

anvirus

Apr 13

is there another quantised varint to be posted for other than MLX

Volodymyryx

Apr 13

Yes, which one world you like?

Volodymyryx

Apr 13

There is a queue, we are working through it to prepare the models for deployment

anvirus

Apr 13

Yes, which one world you like?

gemma-4-26B-A4B rotorquant q4 m

Volodymyryx

Apr 13

You should find what you need now

anvirus

May 19

You should find what you need now

can you make a rotorquant of "Jiunsong/supergemma4-26b-uncensored-gguf-v2"

majentik

Owner Jul 9

@anvirus Thanks for the suggestion — we generally quantize from official upstream releases only, so we can pin provenance and licensing cleanly; third-party finetunes like that one aren't in the pipeline. The good news: the standard llama.cpp/MLX tooling we use works on it directly if you want to run the same recipe yourself (convert to BF16 GGUF → llama-quantize).

majentik

Owner 11 days ago

Closing as answered: the requested 4-bit build was published, and per our policy we only quantize official upstream releases (third-party finetunes excluded). Reopen if you need anything else.

majentik changed discussion status to closed 11 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