← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
1k
tokens
712.6
PP tok/s
54.9
TG tok/s
1437
TTFT (ms)
66.3
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.2.11
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 712.6 | 54.9 | 66.3 GB | current |
| 4k | 738.3 | 52.4 | 66.7 GB | view |
| 8k | 723.3 | 47.2 | 67.0 GB | view |
| 16k | 677.1 | 36.7 | 67.7 GB | view |
| 32k | 598.3 | 24.5 | 69.1 GB | view |
| 64k | 469.9 | 15.2 | 71.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 54.9 | 1.00× |
| 2× | 88.4 | 1.61× |
| 4× | 125.7 | 2.29× |
| 8× | 166.5 | 3.03× |