← Back to community benchmarks
Laguna-XS-2.1
Performance
32k
tokens
1,085
PP tok/s
55.4
TG tok/s
30216
TTFT (ms)
20.0
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.5.2.dev1
macOS
macOS 26.5.2
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,121 | 85.4 | 18.1 GB | view |
| 4k | 1,629 | 82.0 | 18.3 GB | view |
| 8k | 1,332 | 76.3 | 18.6 GB | view |
| 16k | 1,465 | 66.2 | 19.0 GB | view |
| 32k | 1,085 | 55.4 | 20.0 GB | current |
| 64k | 841.0 | 42.8 | 22.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 85.4 | 1.00× |
| 2× | 119.9 | 1.40× |
| 4× | 176.2 | 2.06× |