← Back to community benchmarks

Qwen3.5-9B-DeepSeek-V4-Flash-oQ4-mtp

M4 (10c) · 24 GB · 4bit · 2026-05-20

Performance

8k

tokens

170.0

PP tok/s

24.9

TG tok/s

48191

TTFT (ms)

7.1

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 24 GB

GPU Cores 10

Software

oMLX v0.3.9.dev2

macOS macOS 26.4.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	176.3	27.3	6.0 GB	view
4k	176.4	26.8	6.6 GB	view
8k	170.0	24.9	7.1 GB	current
16k	145.7	20.5	8.0 GB	view
32k	124.3	17.4	9.8 GB	view