Запустить через Basalt Run with Basalt Basalt on GitHub

⚡ Запустить в Basalt (macOS 27+ · Apple Silicon, без Python) · Upstream source: mlx-community/gemma-4-12B-it-qat-4bit:

basalt serve --model goodmai/gemma-4-12B-it-qat-4bit --rest

mlx-community/gemma-4-12B-it-qat-4bit

Use with mlx

pip install -U mlx-vlm
python -m mlx_vlm.generate --model mlx-community/gemma-4-12B-it-qat-4bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
Downloads last month
42
Safetensors
Model size
12B params
Tensor type
U32
·
BF16
·
MLX
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Space using goodmai/gemma-4-12B-it-qat-4bit 1

Collection including goodmai/gemma-4-12B-it-qat-4bit