Instructions to use majentik/gemma-4-26B-A4B-it-TurboQuant-MLX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use majentik/gemma-4-26B-A4B-it-TurboQuant-MLX-8bit 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-TurboQuant-MLX-8bit")
config = load_config("majentik/gemma-4-26B-A4B-it-TurboQuant-MLX-8bit")

# 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-TurboQuant-MLX-8bit 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-TurboQuant-MLX-8bit"

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-TurboQuant-MLX-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use majentik/gemma-4-26B-A4B-it-TurboQuant-MLX-8bit 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-TurboQuant-MLX-8bit"

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-TurboQuant-MLX-8bit

Run Hermes

hermes

OpenClaw new

How to use majentik/gemma-4-26B-A4B-it-TurboQuant-MLX-8bit 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-TurboQuant-MLX-8bit"

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-TurboQuant-MLX-8bit" \
  --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-4-26B-A4B-it-TurboQuant-MLX-8bit

Commit History

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

aa092f7
verified

majentik commited on 13 days ago

Remove links to retired card-only KV-docs repos

8f9d931
verified

majentik commited on 13 days ago

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

a2129b2
verified

majentik commited on 19 days ago

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

40ae22c
verified

majentik commited on 24 days ago

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

84c00cf
verified

majentik commited on 26 days ago

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

bd7e27b
verified

majentik commited on May 6

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

260f213
verified

majentik commited on Apr 17

Add MLX quantized model with KV cache compression

238c004
verified

majentik commited on Apr 13

initial commit

d8ad323
verified

majentik commited on Apr 13

Commit History

Card accuracy sweep: honest brand labeling, remove dead links, upstream KV tip aa092f7 verified

Remove links to retired card-only KV-docs repos 8f9d931 verified

docs: upstream-first KV-cache guidance (q8_0/q4_0, mainline Hadamard rotation); fork demoted to experimental a2129b2 verified

docs: remove AWQ variants from family table (AWQ lane paused, repos private) 40ae22c verified

fix: family model links majentik/gemma4-* -> majentik/gemma-4-* (reported by @shramee in gemma-4-31B-TurboQuant-MLX-4bit#1) 84c00cf verified

docs: Tier 2 polish — variant matrix + quant trade-off bd7e27b verified

chore(card): enrich YAML frontmatter (pipeline_tag, language, library_name, inference) 260f213 verified

Add MLX quantized model with KV cache compression 238c004 verified

initial commit d8ad323 verified

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

aa092f7
verified

Remove links to retired card-only KV-docs repos

8f9d931
verified

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

a2129b2
verified

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

40ae22c
verified

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

84c00cf
verified

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

bd7e27b
verified

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

260f213
verified

Add MLX quantized model with KV cache compression

238c004
verified

initial commit

d8ad323
verified