← Back to community benchmarks

Qwen3-8B

M4 Max (40c) · 48 GB · 4bit · 2026-04-17

Performance

8k

tokens

782.6

PP tok/s

67.5

TG tok/s

10468

TTFT (ms)

6.0

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 48 GB

GPU Cores 40

Software

oMLX v0.3.5

macOS macOS 26.4.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	829.8	88.0	5.0 GB	view
4k	853.0	79.0	5.5 GB	view
8k	782.6	67.5	6.0 GB	current
16k	661.9	52.1	7.1 GB	view
32k	527.2	37.1	9.4 GB	view
64k	366.2	21.3	14.1 GB	view