Instructions to use majentik/gemma-4-E2B-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-E2B-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-E2B-it-RotorQuant-MLX-2bit")
config = load_config("majentik/gemma-4-E2B-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-E2B-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-E2B-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-E2B-it-RotorQuant-MLX-2bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use majentik/gemma-4-E2B-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-E2B-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-E2B-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"

Hermes Agent

How to use majentik/gemma-4-E2B-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-E2B-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-E2B-it-RotorQuant-MLX-2bit

Run Hermes

hermes

Atomic Chat

gemma-4-E2B-it-RotorQuant-MLX-2bit

Commit History

Fix quantization metadata: top-level bits 2 (matches tensor data)

0dc2308
verified

majentik commited on 5 days ago

Card accuracy pass 2: remove unmeasured speed claims, honest brand labels

9631011
verified

majentik commited on 26 days ago

Card accuracy sweep: honest brand labeling, remove dead links, upstream KV tip

a5e8447
verified

majentik commited on 26 days ago

Remove links to retired card-only KV-docs repos

6ae8797
verified

majentik commited on 26 days ago

docs: upstream-first KV-cache guidance (q8_0/q4_0, mainline Hadamard rotation); fork demoted to experimental

0a94565
verified

majentik commited on Jul 14

docs: remove AWQ variants from family table (AWQ lane paused, repos private)

0c57e8e
verified

majentik commited on Jul 9

fix: family model links majentik/gemma4-* -> majentik/gemma-4-* (reported by @shramee in gemma-4-31B-TurboQuant-MLX-4bit#1)

a8c78f1
verified

majentik commited on Jul 7

docs: Tier 2 polish — variant matrix + quant trade-off

79441a4
verified

majentik commited on May 6

chore(card): enrich YAML frontmatter (pipeline_tag, language, library_name, inference)

043c673
verified

majentik commited on Apr 17

Add MLX quantized model with KV cache compression

a74ffb5
verified

majentik commited on Apr 13

initial commit

b1e8988
verified

majentik commited on Apr 13

Commit History

Fix quantization metadata: top-level bits 2 (matches tensor data) 0dc2308 verified

Card accuracy pass 2: remove unmeasured speed claims, honest brand labels 9631011 verified

Card accuracy sweep: honest brand labeling, remove dead links, upstream KV tip a5e8447 verified

Remove links to retired card-only KV-docs repos 6ae8797 verified

docs: upstream-first KV-cache guidance (q8_0/q4_0, mainline Hadamard rotation); fork demoted to experimental 0a94565 verified

docs: remove AWQ variants from family table (AWQ lane paused, repos private) 0c57e8e verified

fix: family model links majentik/gemma4-* -> majentik/gemma-4-* (reported by @shramee in gemma-4-31B-TurboQuant-MLX-4bit#1) a8c78f1 verified

docs: Tier 2 polish — variant matrix + quant trade-off 79441a4 verified

chore(card): enrich YAML frontmatter (pipeline_tag, language, library_name, inference) 043c673 verified

Add MLX quantized model with KV cache compression a74ffb5 verified

initial commit b1e8988 verified

Fix quantization metadata: top-level bits 2 (matches tensor data)

0dc2308
verified

Card accuracy pass 2: remove unmeasured speed claims, honest brand labels

9631011
verified

Card accuracy sweep: honest brand labeling, remove dead links, upstream KV tip

a5e8447
verified

Remove links to retired card-only KV-docs repos

6ae8797
verified

docs: upstream-first KV-cache guidance (q8_0/q4_0, mainline Hadamard rotation); fork demoted to experimental

0a94565
verified

docs: remove AWQ variants from family table (AWQ lane paused, repos private)

0c57e8e
verified

fix: family model links majentik/gemma4-* -> majentik/gemma-4-* (reported by @shramee in gemma-4-31B-TurboQuant-MLX-4bit#1)

a8c78f1
verified

docs: Tier 2 polish — variant matrix + quant trade-off

79441a4
verified

chore(card): enrich YAML frontmatter (pipeline_tag, language, library_name, inference)

043c673
verified

Add MLX quantized model with KV cache compression

a74ffb5
verified

initial commit

b1e8988
verified