← Back to community benchmarks

Qwen3.5-VL-4B-4bitCRACK

M4 Pro (20c) · 64 GB · 4bit · 2026-03-11

Performance

1k

tokens

785.0

PP tok/s

81.0

TG tok/s

1305

TTFT (ms)

4.0

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.2.8

macOS macOS 15.7.3

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	81.0	1.00×
2×	147.9	1.83×
4×	163.7	2.02×
8×	144.4	1.78×