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

Libraries

How to use pipenetwork/Gemma-4-26B-A4B-it-MLX-8bit with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("pipenetwork/Gemma-4-26B-A4B-it-MLX-8bit")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use pipenetwork/Gemma-4-26B-A4B-it-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 "pipenetwork/Gemma-4-26B-A4B-it-MLX-8bit"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "pipenetwork/Gemma-4-26B-A4B-it-MLX-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use pipenetwork/Gemma-4-26B-A4B-it-MLX-8bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "pipenetwork/Gemma-4-26B-A4B-it-MLX-8bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "pipenetwork/Gemma-4-26B-A4B-it-MLX-8bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "pipenetwork/Gemma-4-26B-A4B-it-MLX-8bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use pipenetwork/Gemma-4-26B-A4B-it-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 "pipenetwork/Gemma-4-26B-A4B-it-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 pipenetwork/Gemma-4-26B-A4B-it-MLX-8bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use pipenetwork/Gemma-4-26B-A4B-it-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 "pipenetwork/Gemma-4-26B-A4B-it-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 "pipenetwork/Gemma-4-26B-A4B-it-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-MLX-8bit

MLX (Apple Silicon) conversion of google/gemma-4-26B-A4B-it (Mixture-of-Experts, ~4B active), quantized to 8-bit · near-lossless. Text-only build.

Quantizations

Part of the Gemma-4-26B-A4B-it MLX collection.

Variant	Notes
4-bit	4-bit · community build (mlx-community)
8-bit (this repo)	8-bit · near-lossless
6-bit	6-bit · high quality
5-bit	5-bit

Use with mlx-lm

pip install mlx-lm
python -m mlx_lm generate --model pipenetwork/Gemma-4-26B-A4B-it-MLX-8bit --prompt "Explain Mixture-of-Experts briefly." -m 256

Validation

Smoke-tested locally: loads and generates coherent text.

License

Apache 2.0 (inherited from base). Quantization config: {"group_size": 64, "bits": 8, "mode": "affine", "language_model.model.layers.0.router.proj": {"group_size": 64, "bits": 8}, "language_model.model.layers.1.router.proj": {"group_size": 64, "bits": 8}, .