← Back to community benchmarks
Laguna-S-2.1-oQ5e
Performance
8k
tokens
387.9
PP tok/s
24.4
TG tok/s
21122
TTFT (ms)
74.4
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
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 232.1 | 24.6 | 73.6 GB | view |
| 4k | 337.9 | 21.0 | 73.9 GB | view |
| 8k | 387.9 | 24.4 | 74.4 GB | current |
| 16k | 407.4 | 27.4 | 75.9 GB | view |
| 32k | 429.9 | 27.6 | 78.9 GB | view |
| 64k | 411.6 | 24.0 | 84.9 GB | view |
| 128k | 355.1 | 20.1 | 96.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 24.6 | 1.00× |
| 2× | 43.6 | 1.77× |
| 4× | 50.1 | 2.04× |