← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
8k
tokens
720.5
PP tok/s
46.7
TG tok/s
11369
TTFT (ms)
67.0
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 710.8 | 53.9 | 66.3 GB | view |
| 4k | 737.5 | 51.3 | 66.7 GB | view |
| 8k | 720.5 | 46.7 | 67.0 GB | current |
| 16k | 677.4 | 38.0 | 67.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 53.9 | 1.00× |
| 2× | 87.5 | 1.62× |
| 4× | 126.1 | 2.34× |