← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
8k
tokens
416.2
PP tok/s
28.4
TG tok/s
19681
TTFT (ms)
95.4
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.14
macOS
macOS 15.7.4
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 446.3 | 34.2 | 94.8 GB | view |
| 4k | 465.3 | 32.9 | 95.1 GB | view |
| 8k | 416.2 | 28.4 | 95.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 34.2 | 1.00× |
| 2× | 52.0 | 1.52× |
| 4× | 56.2 | 1.64× |
| 8× | 65.3 | 1.91× |