← Back to community benchmarks

Qwen3___5-4B

M1 Max (32c) · 32 GB · unknown · 2026-03-10

Performance

4k

tokens

528.1

PP tok/s

7.8

TG tok/s

7756

TTFT (ms)

12.1

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 32 GB

GPU Cores 32

Software

oMLX v0.2.6

macOS macOS 26.3

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	528.0	7.8	12.0 GB	view
4k	528.1	7.8	12.1 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	7.8	1.00×
2×	10.5	1.35×
4×	20.8	2.67×