Joe Muller(@BosonJoe):GLM 5.2 @ 19.8 tok/sec on 2 DGX Sparks ⚡️ I switched to a dspark draft model with K=2 (model from @RedHat_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 Muller

@BosonJoe

Local AI enthusiast, suffering from token sickness 2x DGX Spark, 2x RTX 5090

参加 April 2019

1.1K フォロー中 6.9K ファン

Joe Muller@BosonJoe

2026.07.16 18:15

GLM 5.2 @ 19.8 tok/sec on 2 DGX Sparks ⚡️ I switched to a dspark draft model with K=2 (model from @RedHat_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