← Back to community benchmarks

Ternary-Bonsai-8B

M5 Max (40c) · 128 GB · 2bit · 2026-06-04

Performance

4k

tokens

2,957

PP tok/s

129.3

TG tok/s

1385

TTFT (ms)

3.6

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.4.0

macOS macOS 26.5.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,560	157.4	2.9 GB	view
4k	2,957	129.3	3.6 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	157.4	1.00×
2×	188.8	1.20×
4×	217.9	1.38×