← Back to community benchmarks
Bonsai-8B1bit
Performance
1k
tokens
316.9
PP tok/s
62.2
TG tok/s
3231
TTFT (ms)
2.5
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.5.2rc2
macOS
macOS 26.5.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 316.9 | 62.2 | 2.5 GB | current |
| 4k | 453.0 | 49.2 | 3.2 GB | view |
| 8k | 438.6 | 38.8 | 4.1 GB | view |
| 16k | 397.7 | 27.5 | 5.8 GB | view |
| 32k | 330.4 | 17.4 | 9.2 GB | view |
| 64k | 252.1 | 9.3 | 15.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 62.2 | 1.00× |
| 2× | 67.0 | 1.08× |
| 4× | 69.7 | 1.12× |