← Back to community benchmarks

Carnice-V2-27b-oQ3

M1 Max (24c) · 32 GB · 3bit · 2026-06-05

Performance

4k

tokens

111.3

PP tok/s

15.6

TG tok/s

36815

TTFT (ms)

13.9

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 32 GB

GPU Cores 24

Software

oMLX v0.4.2.dev1

macOS macOS 26.3

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	102.7	15.8	13.0 GB	view
4k	111.3	15.6	13.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	15.8	1.00×
2×	18.0	1.14×
4×	20.2	1.28×