← Back to community benchmarks
Ternary-Bonsai-8B
Performance
1k
tokens
79.8
PP tok/s
9.1
TG tok/s
12838
TTFT (ms)
2.9
Peak mem (GB)
Hardware
Chip
M3 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.2
Context
1,024
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 9.1 | 1.00× |
| 2× | 10.6 | 1.16× |
| 4× | 12.5 | 1.37× |
| 8× | 12.6 | 1.38× |