← Back to community benchmarks

Qwen3.5-0.8B

M1 Pro (14c) · 16 GB · 4bit · 2026-03-10

Performance

1k

tokens

1,436

PP tok/s

173.0

TG tok/s

713

TTFT (ms)

1.7

Peak mem (GB)

Hardware

Chip M1 Pro (14c)

Memory 16 GB

GPU Cores 14

Software

oMLX v0.2.6

macOS macOS 26.3

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,436	173.0	1.7 GB	current
4k	1,475	157.4	1.9 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	173.0	1.00×
2×	216.8	1.25×
4×	234.3	1.35×