← Back to community benchmarks

Qwen3.5-122B-A10B-VisionMixed

M5 Max (40c) · 128 GB · 4bit · 2026-04-04
Performance
1k
tokens
992.9
PP tok/s
36.6
TG tok/s
1031
TTFT (ms)
73.3
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
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 992.9 36.6 73.3 GB current
4k 1,470 35.9 74.7 GB view
8k 1,521 34.9 75.3 GB view