← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
64k
tokens
474.9
PP tok/s
29.4
TG tok/s
137987
TTFT (ms)
71.9
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 710.4 | 53.2 | 66.3 GB | view |
| 4k | 739.5 | 52.8 | 66.7 GB | view |
| 8k | 721.8 | 48.1 | 67.0 GB | view |
| 16k | 678.4 | 44.8 | 67.7 GB | view |
| 32k | 599.1 | 38.1 | 69.1 GB | view |
| 64k | 474.9 | 29.4 | 71.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 53.2 | 1.00× |
| 2× | 87.6 | 1.65× |
| 4× | 126.0 | 2.37× |
| 8× | 168.0 | 3.16× |