← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
16k
tokens
514.3
PP tok/s
42.6
TG tok/s
31857
TTFT (ms)
67.7
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.13
macOS
macOS 26.3
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 545.5 | 56.0 | 66.3 GB | view |
| 4k | 560.5 | 53.6 | 66.7 GB | view |
| 8k | 546.6 | 50.8 | 67.0 GB | view |
| 16k | 514.3 | 42.6 | 67.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 56.0 | 1.00× |
| 2× | 87.0 | 1.55× |
| 4× | 111.4 | 1.99× |
| 8× | 136.1 | 2.43× |