← Back to community benchmarks

Jackrong:Qwopus3.5-9B-v3

M1 Max (24c) · 32 GB · bf16 · 2026-04-05

Performance

4k

tokens

387.1

PP tok/s

18.2

TG tok/s

10580

TTFT (ms)

18.3

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 32 GB

GPU Cores 24

Software

oMLX v0.3.4

macOS macOS 26.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	345.2	19.5	17.5 GB	view
4k	387.1	18.2	18.3 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	19.5	1.00×
2×	12.0	0.62×
4×	23.0	1.18×