Instructions to use spicyneuron/Gemma-4-26B-A4B-MLX-4.7bit-vision with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use spicyneuron/Gemma-4-26B-A4B-MLX-4.7bit-vision 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("spicyneuron/Gemma-4-26B-A4B-MLX-4.7bit-vision")
config = load_config("spicyneuron/Gemma-4-26B-A4B-MLX-4.7bit-vision")

# 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 spicyneuron/Gemma-4-26B-A4B-MLX-4.7bit-vision with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "spicyneuron/Gemma-4-26B-A4B-MLX-4.7bit-vision"

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": "spicyneuron/Gemma-4-26B-A4B-MLX-4.7bit-vision"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use spicyneuron/Gemma-4-26B-A4B-MLX-4.7bit-vision with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "spicyneuron/Gemma-4-26B-A4B-MLX-4.7bit-vision"

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 "spicyneuron/Gemma-4-26B-A4B-MLX-4.7bit-vision" \
  --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 spicyneuron/Gemma-4-26B-A4B-MLX-4.7bit-vision 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 "spicyneuron/Gemma-4-26B-A4B-MLX-4.7bit-vision"

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 spicyneuron/Gemma-4-26B-A4B-MLX-4.7bit-vision

Run Hermes

hermes

Gemma-4-26B-A4B-it optimized for MLX. This quant supports image input and requires a vision-enabled MLX server.

EDIT April 5, 2026: Updated model for better performance / speed tradeoff, plus full precision vision embedding. Added benchmarks.

Usage

# Start server at http://localhost:8080/chat/completions
uvx --from mlx-vlm --with torchvision \
  mlx_vlm.server \
  --host 127.0.0.1 \
  --port 8080 \
  --model spicyneuron/Gemma-4-26B-A4B-MLX-4.7bit-vision

Methodology

Quantized using a custom script inspired by Unsloth/AesSedai/ubergarm style mixed-precision GGUFs. MLX quantization options differ than llama.cpp, but the principles are the same:

Sensitive layers like MoE routing, attention, and output embeddings get higher precision
More tolerant layers like MoE experts get lower precision

Benchmarks

metric	mlx-community/gemma-4-26b-a4b-it-4bit	unsloth/gemma-4-26b-a4b-it-UD-MLX-4bit	4.7 bit (this model)
bpw	4.587	4.743	4.704
peak mem	15.312	15.804	15.681
prompt proc (1024)	2514.427	2508.474	2501.617
token gen (512)	97.214	92.890	91.860
perplexity	146.663 ± 0.921	211.070 ± 1.378	133.539 ± 0.827
hellaswag	0.525 ± 0.011	0.531 ± 0.011	0.532 ± 0.011
piqa	0.72 ± 0.01	0.712 ± 0.011	0.719 ± 0.01
winogrande	0.635 ± 0.014	0.635 ± 0.014	0.639 ± 0.014

Bits per weight calculated against only the language_model weights.
Perplexity in Gemma 4 was surprisingly high but seemed consistent across my trials. Could be a side effect of using allenai/tulu-3-sft-mixture. Best to interpret it as weaker signal than the other benchmark results.

Tested with:

mlx_lm.perplexity --sequence-length 4096 --seed 123
mlx_lm.benchmark --prompt-tokens 1024 --generation-tokens 512 --num-trials 5
mlx_lm.evaluate --tasks hellaswag --seed 123 --num-shots 0 --limit 2000
mlx_lm.evaluate --tasks piqa --seed 123 --num-shots 0 --limit 2000
mlx_lm.evaluate --tasks winogrande --seed 123 --num-shots 0 --limit 2000