← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
8k
tokens
561.2
PP tok/s
55.7
TG tok/s
14596
TTFT (ms)
68.5
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.19.dev2
macOS
macOS 26.3.2
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 578.0 | 60.8 | 66.4 GB | view |
| 4k | 603.9 | 59.6 | 67.9 GB | view |
| 8k | 561.2 | 55.7 | 68.5 GB | current |
| 16k | 484.4 | 39.6 | 69.7 GB | view |
| 32k | 427.0 | 40.0 | 72.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 60.8 | 1.00× |
| 2× | 89.4 | 1.47× |
| 4× | 109.3 | 1.80× |
| 8× | 122.6 | 2.02× |