← Back to community benchmarks
Qwen3.5-122B-A10BQ3.5-VL
Performance
4k
tokens
333.0
PP tok/s
11.0
TG tok/s
12301
TTFT (ms)
55.5
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
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 309.5 | 11.4 | 54.9 GB | view |
| 4k | 333.0 | 11.0 | 55.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 11.4 | 1.00× |
| 2× | 19.9 | 1.75× |
| 4× | 40.5 | 3.55× |