← Back to community benchmarks
Laguna-S-2.1-oQ6e
Performance
16k
tokens
695.0
PP tok/s
46.3
TG tok/s
23575
TTFT (ms)
89.2
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.5.3
macOS
macOS 26.5.2
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 677.6 | 51.3 | 87.0 GB | view |
| 4k | 712.3 | 51.4 | 87.3 GB | view |
| 8k | 733.0 | 47.6 | 87.7 GB | view |
| 16k | 695.0 | 46.3 | 89.2 GB | current |
| 32k | 658.7 | 38.4 | 92.2 GB | view |
| 64k | 522.6 | 27.6 | 98.2 GB | view |
| 128k | 314.9 | 16.7 | 110.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 51.3 | 1.00× |
| 2× | 31.8 | 0.62× |
| 4× | 41.1 | 0.80× |