← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
32k
tokens
766.6
PP tok/s
28.4
TG tok/s
42745
TTFT (ms)
128.9
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.18
macOS
macOS 26.2
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 861.8 | 38.7 | 123.3 GB | view |
| 4k | 956.1 | 37.3 | 124.8 GB | view |
| 8k | 940.6 | 35.8 | 125.4 GB | view |
| 16k | 881.2 | 33.2 | 126.5 GB | view |
| 32k | 766.6 | 28.4 | 128.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 38.7 | 1.00× |
| 2× | 63.4 | 1.64× |
| 4× | 92.9 | 2.40× |
| 8× | 132.7 | 3.43× |