← Back to community benchmarks

Qwen3.5-VL-2B-4bitCRACK

M3 (10c) · 24 GB · 4bit · 2026-03-10

Performance

4k

tokens

862.6

PP tok/s

55.9

TG tok/s

4748

TTFT (ms)

2.5

Peak mem (GB)

Hardware

Chip M3 (10c)

Memory 24 GB

GPU Cores 10

Software

oMLX v0.2.6

macOS macOS 15.7.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	857.7	72.4	2.5 GB	view
4k	862.6	55.9	2.5 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	72.4	1.00×
2×	132.6	1.83×
4×	171.6	2.37×