← Back to community benchmarks

Llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning

M2 Max (38c) · 96 GB · fp16 · 2026-05-18

Performance

16k

tokens

428.9

PP tok/s

13.6

TG tok/s

38207

TTFT (ms)

17.4

Peak mem (GB)

Hardware

Chip M2 Max (38c)

Memory 96 GB

GPU Cores 38

Software

oMLX v0.3.9.dev2

macOS macOS 15.7.3

Context 16,384