← Back to community benchmarks

Qwen3.5-122B-A10B-oQ2

M5 Max (40c) · 128 GB · 2bit · 2026-04-01
Performance
4k
tokens
1,451
PP tok/s
54.6
TG tok/s
2824
TTFT (ms)
42.8
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.0
macOS macOS 26.4
Context 4,096