← Back to community benchmarks
Qwen3.5-122B-A10BQ3.5-VL
Performance
1k
tokens
273.6
PP tok/s
11.4
TG tok/s
3742
TTFT (ms)
54.9
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
96 GB
GPU Cores
38
Software
oMLX
v0.2.13
macOS
macOS 15.7.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 273.6 | 11.4 | 54.9 GB | current |
| 4k | 327.8 | 11.0 | 55.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 11.4 | 1.00× |
| 2× | 20.3 | 1.78× |
| 4× | 40.1 | 3.52× |