← Back to community benchmarks

Qwen3.5-122B-A10B-oQ5

M5 Max (40c) · 128 GB · 5bit · 2026-03-30
Performance
8k
tokens
1,469
PP tok/s
40.2
TG tok/s
5576
TTFT (ms)
83.8
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.24
macOS macOS 26.4
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,165 43.3 81.7 GB view
4k 1,507 41.9 83.2 GB view
8k 1,469 40.2 83.8 GB current