Performance
4k
tokens
661.7
PP tok/s
22.8
TG tok/s
6190
TTFT (ms)
20.7
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 646.7 | 24.1 | 18.8 GB | view |
| 4k | 661.7 | 22.8 | 20.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 24.1 | 1.00× |
| 2× | 38.7 | 1.61× |
| 4× | 47.2 | 1.96× |