← Back to community benchmarks

Impish_Bloodmoon_12B

M4 (10c) · 24 GB · 4bit · 2026-04-30

Performance

1k

tokens

144.8

PP tok/s

15.2

TG tok/s

7076

TTFT (ms)

7.1

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 24 GB

GPU Cores 10

Software

oMLX v0.3.8

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	144.8	15.2	7.1 GB	current
4k	142.0	14.0	7.7 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	15.2	1.00×
2×	29.7	1.95×
4×	34.9	2.30×