← Back to community benchmarks
wang-yang--Ornith-1.0-35B-MTPLX
Performance
195k
tokens
457.0
PP tok/s
44.8
TG tok/s
437646
TTFT (ms)
24.6
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.5.1
macOS
macOS 26.5.2
Context
200,000
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,761 | 96.9 | 19.3 GB | view |
| 4k | 1,831 | 98.0 | 20.0 GB | view |
| 8k | 1,734 | 92.8 | 20.2 GB | view |
| 16k | 1,544 | 94.0 | 20.3 GB | view |
| 32k | 1,267 | 80.6 | 20.6 GB | view |
| 64k | 934.8 | 68.4 | 21.9 GB | view |
| 128k | 626.1 | 52.6 | 23.3 GB | view |
| 195k | 457.0 | 44.8 | 24.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 96.9 | 1.00× |
| 2× | 167.8 | 1.73× |
| 4× | 352.8 | 3.64× |