← Back to community benchmarks
Harmonic-Hermes-9B
Performance
4k
tokens
2,779
PP tok/s
57.6
TG tok/s
1474
TTFT (ms)
10.6
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.4
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,979 | 59.0 | 9.9 GB | view |
| 4k | 2,779 | 57.6 | 10.6 GB | current |
| 8k | 2,840 | 55.9 | 11.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 59.0 | 1.00× |
| 2× | 110.8 | 1.88× |
| 4× | 150.8 | 2.56× |