← Back to community benchmarks

Qwen3.5-9B-mxfp4

M5 (10c) · 24 GB · 4bit · 2026-03-08

Performance

1k

tokens

215.4

PP tok/s

26.1

TG tok/s

4753

TTFT (ms)

7.2

Peak mem (GB)

Hardware

Chip M5 (10c)

Memory 24 GB

GPU Cores 10

Software

oMLX v0.2.6

macOS macOS 26.4

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	215.4	26.1	7.2 GB	current
4k	214.5	25.3	7.7 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	26.1	1.00×
2×	51.3	1.97×
4×	60.1	2.30×