Skip to content

lfm3: serve LFM3-1.7B on CUDA: NVFP4 and FP8 weight-only, MLX 4-bit (stacked on #1513, #1492 and #1503) - #1508

Draft
jschmied wants to merge 25 commits into
ashhart:mainfrom
jschmied:lfm3-cuda-nvfp4
Draft

lfm3: serve LFM3-1.7B on CUDA: NVFP4 and FP8 weight-only, MLX 4-bit (stacked on #1513, #1492 and #1503)#1508
jschmied wants to merge 25 commits into
ashhart:mainfrom
jschmied:lfm3-cuda-nvfp4

Commits

  1. Commits on Oct 29, 2026

  2. Commits on Oct 30, 2026