Instructions to use OsaurusAI/gemma-4-31B-it-qat-JANG_4M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OsaurusAI/gemma-4-31B-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-4-31B-it-qat-JANG_4M")
config = load_config("OsaurusAI/gemma-4-31B-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-4-31B-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-4-31B-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-4-31B-it-qat-JANG_4M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use OsaurusAI/gemma-4-31B-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-4-31B-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-4-31B-it-qat-JANG_4M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use OsaurusAI/gemma-4-31B-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-4-31B-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-4-31B-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-4-31B-it-qat-JANG_4M / jang_config.json

Osaurus-AI

Add files using upload-large-folder tool

0cfcad7 verified 3 months ago

Raw

History Blame Contribute Delete

1.71 kB

	{
	"version": 2,
	"weight_format": "jang_affine",
	"profile": "JANG_4M",
	"source_model": {
	"name": "gemma-4-31B-it-qat-q4_0-unquantized",
	"architecture": "gemma4_text"
	},
	"has_vision": true,
	"has_audio": false,
	"has_video": false,
	"modalities": {
	"text": true,
	"vision": true,
	"audio": false,
	"video": false
	},
	"quantization": {
	"method": "jang_affine",
	"quantization_backend": "mx.quantize",
	"mode": "affine",
	"group_size": 32,
	"tier_bits": {
	"attention": 8,
	"router": 8,
	"mlp": 4,
	"embed": 16,
	"per_layer_media": 16
	},
	"tied_embedding": "fp16_passthrough",
	"norm_convention": "gemma4_scale_shift_zero",
	"multimodal": "fp16_passthrough_embedders_early_fusion",
	"preserved_modal_components": [
	"vision_embedder"
	],
	"mtp_policy": "none",
	"per_module_override_count": 180,
	"passthrough_tensor_count": 778
	},
	"runtime": {
	"total_weight_bytes": 26516053451,
	"total_weight_gb": 24.69,
	"attention": "hybrid_swa_full",
	"sliding_window": 1024,
	"attention_k_eq_v_on_full_layers": true,
	"full_attention_layers": [
	5,
	11,
	17,
	23,
	29,
	35,
	41,
	47,
	53,
	59
	]
	},
	"capabilities": {
	"reasoning_parser": "gemma4",
	"tool_parser": "gemma4",
	"think_in_template": false,
	"supports_tools": true,
	"supports_thinking": true,
	"family": "gemma4",
	"modality": "vision",
	"modalities": {
	"text": true,
	"vision": true,
	"audio": false,
	"video": false
	},
	"has_vision": true,
	"has_audio": false,
	"has_video": false,
	"cache_type": "kv"
	}
	}