
Joe Muller
@BosonJoe • 7,125 subscribers
Local AI enthusiast, suffering from token sickness 2x DGX Spark, 2x RTX 5090
Videos

GLM 5.2 @ 19.8 tok/sec on 2 DGX Sparks ⚡️ I switched to a dspark draft model with K=2 (model from Red Hat AI) Acceptance is ~68% because the drafter was trained with the full FP8 model... Next step is to fine tune the drafter so acceptance on this super quant goes up
Joe Muller73,297 görüntüleme • 2 ay önce
Daha fazla içerik yok.