← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
4k
tokens
464.3
PP tok/s
32.8
TG tok/s
8822
TTFT (ms)
96.3
Peak mem (GB)
Hardware
Chip
M2 Ultra (76c)
Memory
192 GB
GPU Cores
76
Software
oMLX
v0.2.21
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 406.2 | 34.7 | 94.9 GB | view |
| 4k | 464.3 | 32.8 | 96.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 34.7 | 1.00× |
| 2× | 54.1 | 1.56× |
| 4× | 69.5 | 2.00× |