You can deploy this model and start earning money today!

pipenetwork/
Rio-3.1-Open-30B-MLX-4bit

Name: Rio-3.1-Open-30B-MLX-4bit
Availability: InStock

prefeitura-rio/Rio-3.1-Open-30B

quantized

mit

4-bit

Views

No views yet

Rio-3.1-Open-30B-MLX-4bit

MLX (Apple Silicon) conversion of prefeitura-rio/Rio-3.1-Open-30B (Qwen3-MoE, 128 experts), quantized to 4-bit. First MLX build of this model.

Quantizations

Part of the Rio-3.1-Open-30B MLX collection.

Variant	Notes
8-bit	8-bit · near-lossless
6-bit	6-bit · high quality
5-bit	5-bit
4-bit (this repo)	4-bit · balanced default

Use with mlx-lm

bash

pip install mlx-lm
python -m mlx_lm generate --model pipenetwork/Rio-3.1-Open-30B-MLX-4bit --prompt "Olá, tudo bem?" -m 256

Validation

Smoke-tested locally: loads and generates coherent text.

License

MIT (inherited from base). Quantization config:

{"group_size": 64, "bits": 4, "mode": "affine", "model.layers.0.mlp.gate": {"group_size": 64, "bits": 8}, "model.layers.1.mlp.gate": {"group_size": 64, "bits": 8}, "model.layers.2.mlp.gate": {"group_s