← Back to community benchmarks

Qwen3.5-122B-A10B

M5 Max (40c) · 128 GB · 4bit · 2026-04-03
Performance
1k
tokens
1,070
PP tok/s
65.9
TG tok/s
957
TTFT (ms)
65.6
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.2
macOS macOS 26.4
Context 1,024