← Back to community benchmarks
Qwen3.5-122B-A10B-oQ4
Performance
16k
tokens
3,572
PP tok/s
17.0
TG tok/s
4588
TTFT (ms)
71.2
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.23
macOS
macOS 26.4
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,020 | 57.3 | 67.6 GB | view |
| 4k | 1,443 | 55.1 | 69.0 GB | view |
| 8k | 1,452 | 52.8 | 69.7 GB | view |
| 16k | 3,572 | 17.0 | 71.2 GB | current |
| 32k | 3,500 | 16.8 | 72.6 GB | view |
| 64k | 3,014 | 16.3 | 74.4 GB | view |
| 128k | 2,328 | 15.8 | 77.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 57.3 | 1.00× |
| 2× | 86.9 | 1.52× |
| 4× | 108.8 | 1.90× |