← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
8k
tokens
459.6
PP tok/s
41.2
TG tok/s
17823
TTFT (ms)
67.0
Peak mem (GB)
Hardware
Chip
M2 Ultra (76c)
Memory
192 GB
GPU Cores
76
Software
oMLX
v0.2.11
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 397.7 | 46.9 | 66.3 GB | view |
| 4k | 453.4 | 44.6 | 66.7 GB | view |
| 8k | 459.6 | 41.2 | 67.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 46.9 | 1.00× |
| 2× | 72.2 | 1.54× |
| 4× | 101.5 | 2.16× |
| 8× | 129.5 | 2.76× |