← Back to community benchmarks

HY-MT1.5-7B

M5 Pro (20c) · 64 GB · 4bit · 2026-07-04

Performance

1k

tokens

1,264

PP tok/s

55.7

TG tok/s

810

TTFT (ms)

4.7

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.4.4

macOS macOS 26.5.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,264	55.7	4.7 GB	current
4k	1,566	49.9	5.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	55.7	1.00×
2×	93.4	1.68×
4×	127.9	2.30×
8×	135.2	2.43×