← Back to community benchmarks

Qwen3.5-0.8B

M3 Ultra (80c) · 96 GB · 8bit · 2026-04-28

Performance

1k

tokens

3,801

PP tok/s

310.1

TG tok/s

269

TTFT (ms)

1.9

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 96 GB

GPU Cores 80

Software

oMLX v0.3.7

macOS macOS 26.3.1

Context 1,024