dhara-250m-OptiQ-8bit
> Built with mlx-optiq, the MLX-native toolkit to quantize, fine-tune, and serve LLMs locally on Apple Silicon, no...
Метка: dhara_ar
dhara-250m
A 250M-parameter language model that decodes in three modes from one set of weights, following NVIDIA’s Nemotron-Labs-Diffusion: Tri-Mode...