← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
16k
tokens
501.3
PP tok/s
44.1
TG tok/s
32683
TTFT (ms)
67.7
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.8b1
macOS
macOS 26.3
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 568.3 | 64.3 | 66.3 GB | view |
| 4k | 590.9 | 61.6 | 66.7 GB | view |
| 8k | 543.3 | 54.9 | 67.0 GB | view |
| 16k | 501.3 | 44.1 | 67.7 GB | current |
| 32k | 438.0 | 32.3 | 69.1 GB | view |
| 64k | 332.2 | 21.3 | 71.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 64.3 | 1.00× |
| 2× | 86.4 | 1.34× |
| 4× | 104.8 | 1.63× |
| 8× | 119.1 | 1.85× |