← Back to community benchmarks

Qwen3.5-0.8B

M2 Ultra (76c) · 192 GB · 4bit · 2026-03-09

Performance

64k

tokens

3,899

PP tok/s

86.2

TG tok/s

16808

TTFT (ms)

4.1

Peak mem (GB)

Hardware

Chip M2 Ultra (76c)

Memory 192 GB

GPU Cores 76

Software

oMLX v0.2.6

macOS macOS 15.0

Context 65,536