← Back to community benchmarks

Qwen3.5-VL-2B-4bitCRACK

M4 (10c) · 16 GB · 4bit · 2026-03-11

Performance

4k

tokens

1,044

PP tok/s

57.9

TG tok/s

3925

TTFT (ms)

2.5

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 16 GB

GPU Cores 10

Software

oMLX v0.2.7

macOS macOS 26.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,042	86.4	2.5 GB	view
4k	1,044	57.9	2.5 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	86.4	1.00×
2×	163.7	1.89×
4×	207.5	2.40×