← Back to community benchmarks
Qwen3.5-122B-A10B-oQ2
Performance
64k
tokens
104.3
PP tok/s
18.2
TG tok/s
628177
TTFT (ms)
45.8
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.5.2rc1
macOS
macOS 26.5.2
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 178.4 | 28.0 | 41.4 GB | view |
| 16k | 162.7 | 24.7 | 44.1 GB | view |
| 64k | 104.3 | 18.2 | 45.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 28.0 | 1.00× |
| 2× | 38.1 | 1.36× |
| 4× | 75.7 | 2.70× |