← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
32k
tokens
1,134
PP tok/s
41.8
TG tok/s
28891
TTFT (ms)
71.2
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.0
macOS
macOS 26.4
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,060 | 64.6 | 65.6 GB | view |
| 4k | 1,499 | 61.4 | 67.0 GB | view |
| 8k | 1,422 | 56.1 | 67.7 GB | view |
| 16k | 1,338 | 43.1 | 68.9 GB | view |
| 32k | 1,134 | 41.8 | 71.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 64.6 | 1.00× |
| 2× | 95.5 | 1.48× |
| 4× | 133.1 | 2.06× |
| 8× | 168.3 | 2.61× |