Performance
8k
tokens
216.1
PP tok/s
15.1
TG tok/s
37902
TTFT (ms)
29.9
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
48 GB
GPU Cores
40
Software
oMLX
v0.2.10
macOS
macOS 26.2
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 244.0 | 16.5 | 29.1 GB | view |
| 4k | 242.1 | 16.2 | 29.5 GB | view |
| 8k | 216.1 | 15.1 | 29.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 16.5 | 1.00× |
| 2× | 31.9 | 1.93× |
| 4× | 41.5 | 2.52× |