← Back to community benchmarks
Ornith-1.0-35BoQ8-mtp
Performance
4k
tokens
2,101
PP tok/s
68.2
TG tok/s
1949
TTFT (ms)
36.1
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.4.4
macOS
macOS 26.5.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,323 | 68.5 | 35.4 GB | view |
| 4k | 2,101 | 68.2 | 36.1 GB | current |
| 8k | 2,163 | 67.7 | 36.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 68.5 | 1.00× |
| 2× | 97.4 | 1.42× |
| 4× | 132.2 | 1.93× |