← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
4k
tokens
727.2
PP tok/s
52.3
TG tok/s
5633
TTFT (ms)
66.7
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.2.13
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 650.4 | 55.1 | 66.3 GB | view |
| 4k | 727.2 | 52.3 | 66.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 55.1 | 1.00× |
| 2× | 89.1 | 1.62× |
| 4× | 127.3 | 2.31× |