← Back to community benchmarks

Qwen3.5-2B-Distilled-OPUS-HereticVLM

M4 (10c) · 16 GB · 4bit · 2026-03-16

Performance

4k

tokens

1,048

PP tok/s

81.3

TG tok/s

3910

TTFT (ms)

2.5

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 16 GB

GPU Cores 10

Software

oMLX v0.2.13

macOS macOS 26.3.1

Context 4,096