Context:
homelab
Cluster:
k3s
User:
marcos
Forge Rev:
v1.0 (C17)
K8s Rev:
v1.36.5+k3s1
CPU:
18%
MEM:
32%

describe(bench/mlx-main-apple-m4-cpu-mlp-predict)

Backend:       mlx-main
Device:        apple-m4-cpu
Model:         mlp
Mode:          predict
Runs:          9, since 2026-10-12
Latest:        734.5k samples/s on 2026-10-23
Best:          736.2k samples/s on 2026-10-22, keras 2178dd6

Speed as % of the best run, oldest on the left

100% │  ▄▆▆▇▇██
 87% │▇████████
 75% │█████████
 62% │█████████
 50% │█████████
 37% │█████████
 25% │█████████
  0% │█████████
     └─────────
             now
TIME↓SAMPLES/SΔ PREVKERAS
2026-10-23T03:01Z734.5k-0.2%2178dd6
2026-10-22T03:01Z736.2k+0.9%2178dd6
2026-10-21T03:01Z730.0k-0.1%2178dd6
2026-10-20T18:01Z730.4k+1.4%2178dd6
2026-10-16T03:01Z720.3k+1.0%2178dd6
2026-10-15T03:01Z713.4k+1.5%2178dd6
2026-10-14T03:01Z703.0k+7.8%2178dd6
2026-10-13T03:01Z652.5k+2.3%2178dd6
2026-10-12T06:01Z637.9k2178dd6