← Back to community benchmarks

Qwen3.5-VL-2B-4bitCRACK

M4 (10c) · 16 GB · 4bit · 2026-03-11

Performance

1k

tokens

1,042

PP tok/s

86.4

TG tok/s

983

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 1,024

Performance by Context Length

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

Batching Results

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