← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
1k
tokens
664.7
PP tok/s
52.5
TG tok/s
1540
TTFT (ms)
66.3
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
96 GB
GPU Cores
60
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 664.7 | 52.5 | 66.3 GB | current |
| 4k | 722.5 | 49.9 | 66.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 52.5 | 1.00× |
| 2× | 85.0 | 1.62× |
| 4× | 122.0 | 2.32× |