Hosstia/AliceAI-T5-35B-A0.6B-MLX-4bit

Quantization vs yandex/AliceAI-T5-35B-A0.6B. Hosstia/AliceAI-T5-35B-A0.6B-MLX-4bit is a quantized version of the other (U32/F16).

On the Hub · Downloads on Model Pulse