← Back to community benchmarks

Qwopus3.5-9B-v3

M5 (8c) · 16 GB · 4bit · 2026-04-28

Performance

1k

tokens

435.9

PP tok/s

28.0

TG tok/s

2349

TTFT (ms)

5.7

Peak mem (GB)

Hardware

Chip M5 (8c)

Memory 16 GB

GPU Cores 8

Software

oMLX v0.3.8rc1

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	435.9	28.0	5.7 GB	current
4k	500.1	27.0	6.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	28.0	1.00×
2×	38.4	1.37×
4×	41.3	1.47×