← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
16k
tokens
851.3
PP tok/s
47.6
TG tok/s
19247
TTFT (ms)
68.7
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.4
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 426.4 | 44.2 | 65.6 GB | view |
| 4k | 718.7 | 46.5 | 66.9 GB | view |
| 8k | 800.4 | 46.5 | 67.5 GB | view |
| 16k | 851.3 | 47.6 | 68.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 44.2 | 1.00× |
| 2× | 74.4 | 1.68× |
| 4× | 121.8 | 2.76× |