← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
4k
tokens
1,377
PP tok/s
46.7
TG tok/s
2975
TTFT (ms)
96.3
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.19
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,011 | 48.3 | 94.9 GB | view |
| 4k | 1,377 | 46.7 | 96.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 48.3 | 1.00× |
| 2× | 72.7 | 1.51× |
| 4× | 75.0 | 1.55× |