← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
16k
tokens
1,469
PP tok/s
42.6
TG tok/s
11153
TTFT (ms)
69.7
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.24
macOS
macOS 26.3
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,238 | 52.7 | 66.4 GB | view |
| 4k | 1,601 | 50.1 | 67.9 GB | view |
| 8k | 1,600 | 47.6 | 68.5 GB | view |
| 16k | 1,469 | 42.6 | 69.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 52.7 | 1.00× |
| 2× | 86.7 | 1.65× |
| 4× | 121.7 | 2.31× |