← Back to community benchmarks

Qwen3.5-4B

M1 (8c) · 16 GB · bf16 · 2026-03-11

Performance

1k

tokens

193.4

PP tok/s

6.2

TG tok/s

5296

TTFT (ms)

9.3

Peak mem (GB)

Hardware

Chip M1 (8c)

Memory 16 GB

GPU Cores 8

Software

oMLX v0.2.8

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	193.4	6.2	9.3 GB	current
4k	206.8	6.4	9.5 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	6.2	1.00×
2×	6.6	1.06×
4×	13.2	2.13×