← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
128k
tokens
553.7
PP tok/s
19.6
TG tok/s
236723
TTFT (ms)
86.7
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
131,072
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,064 | 62.2 | 66.4 GB | view |
| 4k | 1,585 | 59.3 | 67.9 GB | view |
| 8k | 1,558 | 57.5 | 68.5 GB | view |
| 16k | 1,412 | 50.0 | 69.7 GB | view |
| 32k | 1,098 | 34.8 | 72.1 GB | view |
| 64k | 825.8 | 29.9 | 77.0 GB | view |
| 128k | 553.7 | 19.6 | 86.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 62.2 | 1.00× |
| 2× | 96.1 | 1.55× |
| 4× | 124.1 | 2.00× |