← Back to community benchmarks

Bonsai-27B1bit

M1 Max (32c) · 32 GB · unknown · 2026-07-21

Performance

4k

tokens

113.5

PP tok/s

23.9

TG tok/s

36075

TTFT (ms)

8.3

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 32 GB

GPU Cores 32

Software

oMLX v0.5.2rc2

macOS macOS 27.0

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	113.5	23.9	8.3 GB	current
16k	118.3	21.9	9.0 GB	view
64k	83.2	13.0	11.4 GB	view