← Back to community benchmarks

Qwen3.5-122B-A10B-oQ4

M5 Max (40c) · 128 GB · 4bit · 2026-04-05
Performance
128k
tokens
614.1
PP tok/s
21.7
TG tok/s
213453
TTFT (ms)
87.1
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.4
macOS macOS 26.4
Context 131,072