← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
1k
tokens
714.0
PP tok/s
55.3
TG tok/s
1434
TTFT (ms)
66.3
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.2.10
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 714.0 | 55.3 | 66.3 GB | current |
| 4k | 738.6 | 52.8 | 66.7 GB | view |
| 8k | 723.9 | 49.9 | 67.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 55.3 | 1.00× |
| 2× | 89.1 | 1.61× |
| 4× | 126.5 | 2.29× |