← Back to community benchmarks

Qwen3.5-122B-A10B-VisionMixed

M5 Max (40c) · 128 GB · 4bit · 2026-04-01
Performance
32k
tokens
454.6
PP tok/s
13.5
TG tok/s
72087
TTFT (ms)
78.9
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.0
macOS macOS 26.4
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 393.3 17.1 73.3 GB view
4k 549.2 16.8 74.7 GB view
8k 557.3 16.0 75.3 GB view
16k 522.5 14.9 76.5 GB view
32k 454.6 13.5 78.9 GB current
64k 335.5 11.1 83.7 GB view