← Back to community benchmarks

Qwen3.5-9B-MXFP4

M1 Pro (14c) · 16 GB · 4bit · 2026-03-11

Performance

4k

tokens

144.8

PP tok/s

26.8

TG tok/s

28291

TTFT (ms)

5.8

Peak mem (GB)

Hardware

Chip M1 Pro (14c)

Memory 16 GB

GPU Cores 14

Software

oMLX v0.2.6

macOS macOS 26.3

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	140.9	28.0	5.5 GB	view
4k	144.8	26.8	5.8 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	28.0	1.00×
2×	30.0	1.07×
4×	31.1	1.11×