← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
4k
tokens
1,499
PP tok/s
46.9
TG tok/s
2733
TTFT (ms)
96.3
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.16
macOS
macOS 26.3.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,152 | 48.9 | 94.9 GB | view |
| 4k | 1,499 | 46.9 | 96.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 48.9 | 1.00× |
| 2× | 72.9 | 1.49× |
| 4× | 85.6 | 1.75× |