← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
4k
tokens
1,428
PP tok/s
59.0
TG tok/s
2868
TTFT (ms)
67.9
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.20
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,057 | 62.3 | 66.4 GB | view |
| 4k | 1,428 | 59.0 | 67.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 62.3 | 1.00× |
| 2× | 94.8 | 1.52× |
| 4× | 117.7 | 1.89× |