← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
16k
tokens
1,324
PP tok/s
40.3
TG tok/s
12372
TTFT (ms)
69.7
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.19
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,267 | 58.8 | 66.4 GB | view |
| 4k | 1,581 | 56.0 | 67.9 GB | view |
| 8k | 1,537 | 54.5 | 68.5 GB | view |
| 16k | 1,324 | 40.3 | 69.7 GB | current |
| 32k | 1,048 | 34.7 | 72.1 GB | view |
| 64k | 736.1 | 28.7 | 77.0 GB | view |
| 128k | 475.6 | 18.3 | 86.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 58.8 | 1.00× |
| 2× | 86.3 | 1.47× |
| 4× | 109.4 | 1.86× |