← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
32k
tokens
1,210
PP tok/s
43.7
TG tok/s
27072
TTFT (ms)
72.1
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.20
macOS
macOS 26.4
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,267 | 61.8 | 66.4 GB | view |
| 4k | 1,606 | 58.3 | 67.9 GB | view |
| 8k | 1,524 | 56.6 | 68.5 GB | view |
| 16k | 1,426 | 52.1 | 69.7 GB | view |
| 32k | 1,210 | 43.7 | 72.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 61.8 | 1.00× |
| 2× | 102.4 | 1.66× |