← Back to community benchmarks

Qwen3.5-9B-DeepSeek-V4-Flash

M4 (10c) · 32 GB · 4bit · 2026-05-12

Performance

4k

tokens

223.6

PP tok/s

21.4

TG tok/s

18318

TTFT (ms)

6.3

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 32 GB

GPU Cores 10

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	217.0	22.0	5.7 GB	view
4k	223.6	21.4	6.3 GB	current
8k	220.3	20.3	6.7 GB	view
16k	204.8	19.1	7.7 GB	view