← Back to community benchmarks
Qwen3.5-122B-A10B-Text-qx85
Performance
32k
tokens
1,076
PP tok/s
29.6
TG tok/s
30447
TTFT (ms)
92.8
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.19
macOS
macOS 26.3.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 991.2 | 55.9 | 87.1 GB | view |
| 4k | 1,440 | 53.9 | 88.6 GB | view |
| 16k | 1,360 | 41.7 | 90.4 GB | view |
| 32k | 1,076 | 29.6 | 92.8 GB | current |
| 64k | 896.6 | 25.2 | 97.6 GB | view |
| 128k | 606.2 | 16.2 | 107.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 55.9 | 1.00× |
| 2× | 83.9 | 1.50× |
| 4× | 105.7 | 1.89× |