← Back to community benchmarks

Qwen3.5-122B-A10B

M5 Max (40c) · 128 GB · 4bit · 2026-07-20
Performance
64k
tokens
894.0
PP tok/s
44.0
TG tok/s
73304
TTFT (ms)
76.4
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.5.1
macOS macOS 26.5.2
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 1,710 60.8 67.0 GB view
16k 1,528 56.0 69.2 GB view
64k 894.0 44.0 76.4 GB current