← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
32k
tokens
402.8
PP tok/s
22.1
TG tok/s
81352
TTFT (ms)
69.1
Peak mem (GB)
Hardware
Chip
M2 Ultra (76c)
Memory
192 GB
GPU Cores
76
Software
oMLX
v0.2.6
macOS
macOS 15.0
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 432.5 | 42.0 | 66.3 GB | view |
| 4k | 456.4 | 38.8 | 66.7 GB | view |
| 8k | 453.5 | 36.4 | 67.0 GB | view |
| 16k | 438.3 | 29.9 | 67.7 GB | view |
| 32k | 402.8 | 22.1 | 69.1 GB | current |
| 64k | 324.5 | 14.8 | 71.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 42.0 | 1.00× |
| 2× | 67.0 | 1.60× |
| 4× | 95.1 | 2.26× |
| 8× | 129.1 | 3.07× |