Instructions to use OsaurusAI/gemma-4-12B-it-JANG_4M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OsaurusAI/gemma-4-12B-it-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-4-12B-it-JANG_4M")
config = load_config("OsaurusAI/gemma-4-12B-it-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-4-12B-it-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-4-12B-it-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-4-12B-it-JANG_4M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use OsaurusAI/gemma-4-12B-it-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-4-12B-it-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-4-12B-it-JANG_4M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use OsaurusAI/gemma-4-12B-it-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-4-12B-it-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-4-12B-it-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 12B-it - JANG_4M

Apple Silicon MLX bundle for Osaurus and compatible vMLX runtimes.

Important update (2026-06-03 4:06 PM PDT): These weights were rebuilt with the verified Gemma 4 12B fix. If you downloaded this repository before 2026-06-03 4:06 PM PDT, delete the local copy and re-download.

Model Details

Property	Value
Base model	`google/gemma-4-12B-it`
Architecture	Gemma 4 unified dense 12B, text + image/audio/video-capable metadata
Format	MLX safetensors
Quantization	JANG mixed precision: attention 8-bit, MLP 4-bit, group size 32; tied embedding and multimodal embedders fp16 passthrough
Tied token embedding	fp16 passthrough (`embed_tokens.weight` is not quantized)
Multimodal embedders	fp16 passthrough
Package size	10.17 GB
Shards	10 safetensors shards
Chat template	Gemma 4 tool-aware template, no default no-thinking thought-channel tail

Runtime Notes

These rebuilt bundles preserve the tied token embedding in fp16 while keeping the main projection weights quantized. This fixes the bad prior artifact where embed_tokens.weight was packed and scaled like a normal linear weight.

The bundle includes generation_config.json, chat_template.jinja, tokenizer_config.json, and processor_config.json for Osaurus/vMLX loading.

Loading

Use Osaurus for local Apple Silicon chat and multimodal workflows, or load the bundle in a compatible MLX runtime:

from mlx_lm import load, generate

model, tokenizer = load("JANGQ-AI/gemma-4-12B-it-JANG_4M")
print(generate(model, tokenizer, "Hello", max_tokens=128))

Verification

Local release check for this rebuild:

Check	Status
`embed_tokens.weight` dtype	fp16
`embed_tokens.scales` / `embed_tokens.biases`	absent
Quantized attention projections	packed uint32
README front matter	valid Hugging Face YAML first
Re-download notice	present after YAML

Downloads last month: 24

Safetensors

Model size

12B params

Tensor type

F16

U32

MLX

Hardware compatibility

Quantized

Model tree for OsaurusAI/gemma-4-12B-it-JANG_4M

Base model

google/gemma-4-12B

Finetuned

google/gemma-4-12B-it

Quantized

(390)

this model