← Back to community benchmarks

Qwopus3.5-9B-v3

M5 (10c) · 32 GB · 4bit · 2026-04-15

Performance

1k

tokens

625.7

PP tok/s

28.0

TG tok/s

1637

TTFT (ms)

5.7

Peak mem (GB)

Hardware

Chip M5 (10c)

Memory 32 GB

GPU Cores 10

Software

oMLX v0.3.5.dev1

macOS macOS 26.4.1

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	28.0	1.00×
2×	54.1	1.93×