← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
32k
tokens
784.2
PP tok/s
35.7
TG tok/s
41785
TTFT (ms)
72.1
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.18
macOS
macOS 26.3.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 920.7 | 51.9 | 66.4 GB | view |
| 8k | 964.7 | 45.7 | 68.5 GB | view |
| 32k | 784.2 | 35.7 | 72.1 GB | current |
| 128k | 384.0 | 18.7 | 86.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 51.9 | 1.00× |
| 2× | 88.4 | 1.70× |
| 4× | 135.9 | 2.62× |
| 8× | 194.0 | 3.74× |