TensorFold/Muse-Glimmer-30B-MLX-4bit

Quantization vs meta-models/Muse-Glimmer-30B. TensorFold/Muse-Glimmer-30B-MLX-4bit is a quantized version of the other (U32/BF16).

2 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse