← Back to community benchmarks

Qwen3.5-2B-Claude-4.6-Opus-Reasoning-Distilled

M2 Ultra (76c) · 192 GB · 8bit · 2026-03-11

Performance

64k

tokens

2,563

PP tok/s

79.0

TG tok/s

25569

TTFT (ms)

5.4

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