← Back to community benchmarks
Apertus-8B-2509
Performance
1k
tokens
434.3
PP tok/s
20.4
TG tok/s
2360
TTFT (ms)
15.5
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.8
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 434.3 | 20.4 | 15.5 GB | current |
| 4k | 428.8 | 19.2 | 16.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.4 | 1.00× |
| 2× | 15.9 | 0.78× |
| 4× | 30.6 | 1.50× |