← Back to community benchmarks

Qwen3.5-4B

M1 (8c) · 16 GB · 4bit · 2026-03-10

Performance

4k

tokens

144.6

PP tok/s

21.4

TG tok/s

28332

TTFT (ms)

4.2

Peak mem (GB)

Hardware

Chip M1 (8c)

Memory 16 GB

GPU Cores 8

Software

oMLX v0.2.6

macOS macOS 26.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	143.0	22.6	3.9 GB	view
4k	144.6	21.4	4.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	22.6	1.00×
2×	33.3	1.47×
4×	34.4	1.52×