Brooooooklyn/Gemma-4-26B-A4B-NVFP4-mlx
Text Generation • 9B • Updated • 442 • 1
NVIDIA NVFP4 → MLX
NVIDIA post-trained NVFP4 checkpoints (ModelOpt PTQ) transcoded to MLX for Apple Silicon / mlx-node, keeping NVIDIA's per-layer bit allocation.