← Back to community benchmarks

Qwopus3.5-9B-v3

M4 Pro (20c) · 24 GB · 4bit · 2026-04-24

Performance

1k

tokens

417.9

PP tok/s

48.5

TG tok/s

2451

TTFT (ms)

5.8

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 24 GB

GPU Cores 20

Software

oMLX v0.3.7

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	417.9	48.5	5.8 GB	current
4k	426.0	47.7	6.5 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	48.5	1.00×
2×	89.9	1.85×
4×	100.3	2.07×