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

Libraries

How to use majentik/gemma-4-31B-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-4-31B-it-RotorQuant-MLX-4bit")
config = load_config("majentik/gemma-4-31B-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-4-31B-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-4-31B-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-4-31B-it-RotorQuant-MLX-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use majentik/gemma-4-31B-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-4-31B-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-4-31B-it-RotorQuant-MLX-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use majentik/gemma-4-31B-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-4-31B-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-4-31B-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"

gemma-4-31B-it-RotorQuant-MLX-4bit

Commit History

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

0fc89a4
verified

majentik commited on 30 days ago

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

fe3f07c
verified

majentik commited on 30 days ago

Remove links to retired card-only KV-docs repos

8a5aa14
verified

majentik commited on 30 days ago

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

41f710b
verified

majentik commited on Jul 14

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

5f721da
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)

a2bc746
verified

majentik commited on Jul 7

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

5896a40
verified

majentik commited on May 6

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

705ecee
verified

majentik commited on Apr 17

Add MLX quantized model with KV cache compression

d5df36e
verified

majentik commited on Apr 13

initial commit

7004aef
verified

majentik commited on Apr 13

Commit History

Card accuracy pass 2: remove unmeasured speed claims, honest brand labels 0fc89a4 verified

Card accuracy sweep: honest brand labeling, remove dead links, upstream KV tip fe3f07c verified

Remove links to retired card-only KV-docs repos 8a5aa14 verified

docs: upstream-first KV-cache guidance (q8_0/q4_0, mainline Hadamard rotation); fork demoted to experimental 41f710b verified

docs: remove AWQ variants from family table (AWQ lane paused, repos private) 5f721da verified

fix: family model links majentik/gemma4-* -> majentik/gemma-4-* (reported by @shramee in gemma-4-31B-TurboQuant-MLX-4bit#1) a2bc746 verified

docs: Tier 2 polish — variant matrix + quant trade-off 5896a40 verified

chore(card): enrich YAML frontmatter (pipeline_tag, language, library_name, inference) 705ecee verified

Add MLX quantized model with KV cache compression d5df36e verified

initial commit 7004aef verified

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

0fc89a4
verified

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

fe3f07c
verified

Remove links to retired card-only KV-docs repos

8a5aa14
verified

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

41f710b
verified

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

5f721da
verified

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

a2bc746
verified

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

5896a40
verified

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

705ecee
verified

Add MLX quantized model with KV cache compression

d5df36e
verified

initial commit

7004aef
verified