← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
4k
tokens
491.4
PP tok/s
39.6
TG tok/s
8336
TTFT (ms)
66.7
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.14
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 464.9 | 41.7 | 66.3 GB | view |
| 4k | 491.4 | 39.6 | 66.7 GB | current |
| 8k | 445.5 | 36.0 | 67.0 GB | view |
| 16k | 402.8 | 31.7 | 67.7 GB | view |
| 32k | 355.2 | 23.2 | 69.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 41.7 | 1.00× |
| 2× | 58.9 | 1.41× |
| 4× | 70.7 | 1.70× |
| 8× | 86.6 | 2.08× |