← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
8k
tokens
1,583
PP tok/s
57.6
TG tok/s
5176
TTFT (ms)
68.5
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.20
macOS
macOS 26.4
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,278 | 63.2 | 66.4 GB | view |
| 4k | 1,618 | 60.7 | 67.9 GB | view |
| 8k | 1,583 | 57.6 | 68.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 63.2 | 1.00× |
| 2× | 102.5 | 1.62× |
| 4× | 133.4 | 2.11× |
| 8× | 169.7 | 2.69× |