← Back to community benchmarks
Ternary-Bonsai-27B
Performance
4k
tokens
410.1
PP tok/s
29.5
TG tok/s
9987
TTFT (ms)
10.3
Peak mem (GB)
Hardware
Chip
M5 Pro (16c)
Memory
48 GB
GPU Cores
16
Software
oMLX
v0.5.2.dev1
macOS
macOS 26.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 413.0 | 30.3 | 8.9 GB | view |
| 4k | 410.1 | 29.5 | 10.3 GB | current |
| 16k | 386.6 | 26.6 | 12.2 GB | view |
| 64k | 285.2 | 18.5 | 19.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 30.3 | 1.00× |
| 2× | 42.2 | 1.39× |
| 4× | 51.0 | 1.68× |