← Back to community benchmarks
Ornith-1.0-35B-5bit
Performance
4k
tokens
1,999
PP tok/s
74.0
TG tok/s
2049
TTFT (ms)
24.9
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.4.4
macOS
macOS 26.5.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,053 | 73.1 | 24.1 GB | view |
| 4k | 1,999 | 74.0 | 24.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 73.1 | 1.00× |
| 2× | 115.8 | 1.58× |
| 4× | 160.8 | 2.20× |
| 8× | 197.5 | 2.70× |