← Back to community benchmarks

Qwen3.5-0.8B

M3 Pro (14c) · 36 GB · 8bit · 2026-04-19

Performance

4k

tokens

2,119

PP tok/s

98.0

TG tok/s

1933

TTFT (ms)

2.1

Peak mem (GB)

Hardware

Chip M3 Pro (14c)

Memory 36 GB

GPU Cores 14

Software

oMLX v0.3.6

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,534	110.6	1.6 GB	view
4k	2,119	98.0	2.1 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	110.6	1.00×
2×	199.6	1.80×
4×	310.1	2.80×