Instructions to use OsaurusAI/gemma-4-E2B-it-qat-JANG_4M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OsaurusAI/gemma-4-E2B-it-qat-JANG_4M 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("OsaurusAI/gemma-4-E2B-it-qat-JANG_4M")
config = load_config("OsaurusAI/gemma-4-E2B-it-qat-JANG_4M")

# 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 OsaurusAI/gemma-4-E2B-it-qat-JANG_4M with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OsaurusAI/gemma-4-E2B-it-qat-JANG_4M"

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": "OsaurusAI/gemma-4-E2B-it-qat-JANG_4M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use OsaurusAI/gemma-4-E2B-it-qat-JANG_4M 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 "OsaurusAI/gemma-4-E2B-it-qat-JANG_4M"

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 OsaurusAI/gemma-4-E2B-it-qat-JANG_4M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use OsaurusAI/gemma-4-E2B-it-qat-JANG_4M with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OsaurusAI/gemma-4-E2B-it-qat-JANG_4M"

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 "OsaurusAI/gemma-4-E2B-it-qat-JANG_4M" \
  --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-E2B-it-qat-JANG_4M / README.md

Osaurus-AI

Add files using upload-large-folder tool

5b32c06 verified 3 months ago

preview code

Raw

History Blame Contribute Delete

2.29 kB

metadata

language:
  - en
library_name: mlx
license: gemma
pipeline_tag: image-text-to-text
base_model: google/gemma-4-E2B-it-qat-q4_0-unquantized
tags:
  - mlx
  - jang
  - jang-4m
  - qat
  - quantized
  - apple-silicon
  - gemma4
  - vision
  - audio

OsaurusAI/gemma-4-E2B-it-qat-JANG_4M

JANG_4M MLX affine bundle converted from google/gemma-4-E2B-it-qat-q4_0-unquantized.

This bundle keeps Gemma 4 bookends and media-sensitive components coherent: token embeddings/output projection, norms, media towers/embedders, and Gemma 4 per-layer embedding/gate/projector tensors are fp16 passthrough; self-attention and MoE router projections are 8-bit affine; decoder MLP/expert bulk is 4-bit affine.

Bundle

Field	Value
Source	`google/gemma-4-E2B-it-qat-q4_0-unquantized`
Architecture	`gemma4` / `Gemma4ForConditionalGeneration`
Text layers	35
Hidden size	1536
Weight format	`jang_affine`
Top-level quantization	bits=8, group_size=32, mode=affine
Tier bits	attention=8, router=8, mlp=4, embed=16, per_layer_media=16
Quantized modules	206 affine bases with `.scales` and `.biases` sidecars
Shards	4 safetensors shards
Capabilities	`multimodal`

Modalities

Modality	Status
Text	supported
Vision	source config present and preserved
Audio	`audio_config` is present and preserved.
Video	No `video_config` is present, so this card does not claim a verified video runtime path.

Runtime support depends on a Gemma 4 compatible MLX/vMLX loader that understands config.json quantization overrides, jang_config.json, and Gemma 4 processor/chat-template files.

Runtime Metadata

config.json has source-derived has_vision, has_audio, has_video, modalities, and capabilities.
tokenizer_config.json includes bos_token_id, eos_token_id, pad_token_id, and the patched Gemma 4 chat template.
processor_config.json is preserved for Gemma 4 multimodal processing.
MTP/speculative drafter weights are not present in the source checkpoint; metadata is mtp: none / mtp_policy: none.