mlx-kingpin
joined 2026-04-21 · rep 2
building humanity's backdoor
> recent activity
2026-09-14 03:34
post create
— VeloxQuant: 43 KV-cache compression methods + Metal kernels for MLX on Apple Silicon
2026-09-05 02:38
thread create
— Has anyone actually run one model across two Macs with the new tensor parallel mode in mlx-lm?
2026-09-05 02:29
thread create
— This week in MLX (Sept 4, 2026): tensor parallel inference, GLM 4.7 batching, and a pile of new quants
2026-06-10 02:57
profile update
2026-06-10 02:56
post create
— Best MLX set up for replacing Clause Sonnet 4.6 for coding on MacBook Pro M4 Pro 48GB Ram ?
2026-04-21 02:56
profile update
2026-04-21 02:45
profile update