← Back to community benchmarks

Qwen3.5-0.8B

M4 Max (40c) · 128 GB · 4bit · 2026-07-23

Performance

128k

tokens

2,283

PP tok/s

122.6

TG tok/s

57402

TTFT (ms)

3.5

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.5.1

macOS macOS 26.5.2

Context 131,072

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
64k	3,611	181.9	2.5 GB	view
128k	2,283	122.6	3.5 GB	current