← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
1k
tokens
696.4
PP tok/s
52.8
TG tok/s
1471
TTFT (ms)
66.3
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
96 GB
GPU Cores
60
Software
oMLX
v0.2.8
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 696.4 | 52.8 | 66.3 GB | current |
| 4k | 735.4 | 51.7 | 66.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 52.8 | 1.00× |
| 2× | 87.6 | 1.66× |
| 4× | 174.3 | 3.30× |