← Back to community benchmarks
Harmonic-Hermes-9B
Performance
4k
tokens
2,930
PP tok/s
30.6
TG tok/s
1398
TTFT (ms)
18.6
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 | 1,764 | 31.1 | 17.5 GB | view |
| 4k | 2,930 | 30.6 | 18.6 GB | current |
| 8k | 2,907 | 30.2 | 18.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 31.1 | 1.00× |
| 2× | 36.6 | 1.18× |
| 4× | 68.5 | 2.20× |