← Back to community benchmarks

Qwen3.5-4B

M4 (8c) · 16 GB · 4bit · 2026-03-12

Performance

4k

tokens

304.4

PP tok/s

35.6

TG tok/s

13457

TTFT (ms)

4.2

Peak mem (GB)

Hardware

Chip M4 (8c)

Memory 16 GB

GPU Cores 8

Software

oMLX v0.2.8

macOS macOS 15.7.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	307.7	36.8	3.9 GB	view
4k	304.4	35.6	4.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	36.8	1.00×
2×	68.3	1.86×
4×	72.4	1.97×