← Back to community benchmarks

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

M3 Ultra (80c) · 512 GB · 4bit · 2026-04-05
Performance
16k
tokens
897.7
PP tok/s
47.0
TG tok/s
18252
TTFT (ms)
68.7
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.3.4
macOS macOS 26.4
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 897.7 47.0 68.7 GB current
32k 783.4 40.2 71.1 GB view