Ssignal
16
·4 days ago·1 signals
Archived topic · source no longer tracked
Auto-fit vs tuned MoE offload: 564 → 1330 pp tok/s, unchanged decode (Qwen3.6-35B-A3B Q6 / RTX 3090)
Heat trend
Collecting trend data
The percentage is based on available heat signal, not comment count or independent people.
This covers generation capability or on-device inference progress — worth tracking for model efficiency, deployment cost, and application openings.