← Back to community benchmarks
community--Qwen3.5-122B-A10B
Performance
4k
tokens
762.9
PP tok/s
45.2
TG tok/s
5369
TTFT (ms)
67.9
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
96 GB
GPU Cores
60
Software
oMLX
v0.2.24
macOS
macOS 26.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 715.6 | 47.4 | 66.4 GB | view |
| 4k | 762.9 | 45.2 | 67.9 GB | current |
| 8k | 749.1 | 42.5 | 68.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 47.4 | 1.00× |
| 2× | 76.6 | 1.62× |
| 4× | 109.8 | 2.32× |