← Back to community benchmarks
Qwen3.5-122B-A10B-5bit
Performance
32k
tokens
974.4
PP tok/s
35.3
TG tok/s
33630
TTFT (ms)
85.5
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.22
macOS
macOS 26.4
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 907.9 | 51.4 | 79.8 GB | view |
| 4k | 1,363 | 48.6 | 81.3 GB | view |
| 16k | 1,120 | 41.8 | 83.1 GB | view |
| 32k | 974.4 | 35.3 | 85.5 GB | current |
| 64k | 753.4 | 27.1 | 90.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 51.4 | 1.00× |
| 2× | 74.8 | 1.46× |
| 4× | 91.1 | 1.77× |