← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
8k
tokens
1,549
PP tok/s
59.9
TG tok/s
5290
TTFT (ms)
67.7
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.0
macOS
macOS 26.4
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,025 | 62.9 | 65.6 GB | view |
| 4k | 1,518 | 63.0 | 67.0 GB | view |
| 8k | 1,549 | 59.9 | 67.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 62.9 | 1.00× |
| 2× | 101.7 | 1.62× |
| 4× | 137.7 | 2.19× |
| 8× | 165.5 | 2.63× |