Instructions to use ToPo-ToPo/gemma-4-E2B-it-qat-mlx-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ToPo-ToPo/gemma-4-E2B-it-qat-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("ToPo-ToPo/gemma-4-E2B-it-qat-mlx-4bit")
config = load_config("ToPo-ToPo/gemma-4-E2B-it-qat-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 ToPo-ToPo/gemma-4-E2B-it-qat-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 "ToPo-ToPo/gemma-4-E2B-it-qat-mlx-4bit"

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": "ToPo-ToPo/gemma-4-E2B-it-qat-mlx-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use ToPo-ToPo/gemma-4-E2B-it-qat-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 "ToPo-ToPo/gemma-4-E2B-it-qat-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 ToPo-ToPo/gemma-4-E2B-it-qat-mlx-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ToPo-ToPo/gemma-4-E2B-it-qat-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 "ToPo-ToPo/gemma-4-E2B-it-qat-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 "ToPo-ToPo/gemma-4-E2B-it-qat-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"

ToPo-ToPo/gemma-4-E2B-it-qat-mlx-4bit

MLX 4-bit conversion of google/gemma-4-E2B-it-qat-q4_0-unquantized, made with mlx-vlm 0.6.3.

Provenance (self-converted)

Source: google/gemma-4-E2B-it-qat-q4_0-unquantized (license: gemma)
Tool: mlx-vlm 0.6.3 mlx_vlm.convert (q_bits=4, group_size=64, affine), ~5.6 bpw
Validated: loads and translates correctly under mlx-vlm 0.6.3.

Usage

from mlx_vlm import load
model, processor = load("ToPo-ToPo/gemma-4-E2B-it-qat-mlx-4bit")

License

Derivative of Google Gemma; governed by the Gemma Terms of Use (https://ai.google.dev/gemma/terms) and Prohibited Use Policy. Converted to MLX.

⚡ MTP drafter (speculative decoding)

Use google/gemma-4-E2B-it-assistant — Google's official MTP drafter for this model. It loads directly in mlx-vlm (>= 0.6.3), needs no conversion, and speculative decoding is lossless. Drafters are size-specific and not interchangeable across Gemma 4 variants.

🔧 Patched chat template

chat_template.jinja differs from Google's Gemma 4 Canonical Chat Template (2026-07-09) by one intentional change; everything else is untouched.

The canonical template suppresses the thinking channel at the start of a normal model turn, but emits nothing after a tool response when enable_thinking is false. The model may then open a thinking channel on its own, and a quantized model sometimes writes the literal word thought into the answer. This patch gives the tool_response branch the same suppression:

{%- elif ns.prev_message_type == 'tool_response' -%}
    {%- if enable_thinking -%}
        {{- '<|channel>thought\n' -}}
    {%- else -%}
        {{- '<|channel>thought\n<channel|>' -}}
    {%- endif -%}
{%- endif -%}

Only that case changes — the other prompt paths render byte-identical to the canonical template. To get stock behaviour, replace chat_template.jinja with the one from the base model repo; the weights are unaffected.