← Back to community benchmarks

Qwen3.5-VL-122B-A10B-4bitCRACK

M3 Ultra (80c) · 512 GB · 4bit · 2026-04-03
Performance
32k
tokens
1,404
PP tok/s
20.3
TG tok/s
23337
TTFT (ms)
100.2
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
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
32k 1,404 20.3 100.2 GB current
128k 779.6 19.0 106.4 GB view