← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
16k
tokens
535.4
PP tok/s
44.5
TG tok/s
30599
TTFT (ms)
67.7
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.6
macOS
macOS 26.4
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 554.3 | 56.9 | 66.3 GB | view |
| 4k | 583.3 | 54.3 | 66.7 GB | view |
| 8k | 570.3 | 50.8 | 67.0 GB | view |
| 16k | 535.4 | 44.5 | 67.7 GB | current |
| 32k | 473.4 | 36.0 | 69.1 GB | view |
| 64k | 379.7 | 25.4 | 71.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 56.9 | 1.00× |
| 2× | 87.0 | 1.53× |
| 4× | 113.9 | 2.00× |
| 8× | 143.8 | 2.53× |