DreamFoundries/MiniCPM5-2B-MLX-8bit


MiniCPM5-2B MLX 8-bit

MLX conversion of openbmb/MiniCPM5-2B, created specifically for MLXHub with the DreamFoundries mlx-lm fork. Affine 8-bit quantization uses group size 64.

The original model is by OpenBMB and is released under Apache-2.0. Comparative quality and performance benchmarks are not available for this conversion.

Use with MLX

from mlx_lm import load, generate

model, tokenizer = load("DreamFoundries/MiniCPM5-2B-MLX-8bit")
response = generate(model, tokenizer, prompt="Hello!", max_tokens=128)
print(response)