← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
1k
tokens
484.6
PP tok/s
43.1
TG tok/s
2113
TTFT (ms)
66.4
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.17
macOS
macOS 15.7.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 484.6 | 43.1 | 66.4 GB | current |
| 4k | 489.7 | 39.5 | 67.9 GB | view |
| 8k | 429.3 | 35.1 | 68.5 GB | view |
| 16k | 398.7 | 31.5 | 69.7 GB | view |
| 32k | 343.1 | 23.0 | 72.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 43.1 | 1.00× |
| 2× | 62.7 | 1.45× |
| 4× | 71.4 | 1.66× |
| 8× | 78.5 | 1.82× |