← Back to community benchmarks
Ornstein-Hermes-3.6-27B-SABER-4bit-MTPLX-Optimized-Speed
Performance
1k
tokens
101.1
PP tok/s
15.7
TG tok/s
10126
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
24 GB
GPU Cores
16
Software
oMLX
v0.3.9
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 101.1 | 15.7 | 15.8 GB | current |
| 4k | 100.7 | 15.1 | 17.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 15.7 | 1.00× |
| 2× | 25.4 | 1.62× |
| 4× | 26.5 | 1.69× |