← Back to community benchmarks
Ternary-Bonsai-27B
Performance
1k
tokens
867.5
PP tok/s
48.1
TG tok/s
1180
TTFT (ms)
8.9
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.5.2rc2
macOS
macOS 26.5.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 867.5 | 48.1 | 8.9 GB | current |
| 4k | 862.7 | 46.1 | 10.3 GB | view |
| 64k | 543.8 | 31.4 | 19.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 48.1 | 1.00× |
| 2× | 74.3 | 1.54× |
| 4× | 188.6 | 3.92× |