← Back to community benchmarks

Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled

M2 Max (38c) · 96 GB · 8bit · 2026-03-15

Performance

1k

tokens

155.2

PP tok/s

20.2

TG tok/s

6598

TTFT (ms)

5.3

Peak mem (GB)

Hardware

Chip M2 Max (38c)

Memory 96 GB

GPU Cores 38

Software

oMLX v0.2.13

macOS macOS 26.2

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	155.2	20.2	5.3 GB	current
4k	160.9	17.6	5.5 GB	view