← Back to community benchmarks

bonsai-2bit-ablg6

M3 Max (30c) · 36 GB · 2bit · 2026-05-14

Performance

4k

tokens

583.7

PP tok/s

68.9

TG tok/s

7017

TTFT (ms)

3.4

Peak mem (GB)

Hardware

Chip M3 Max (30c)

Memory 36 GB

GPU Cores 30

Software

oMLX v0.3.8

macOS macOS 15.7.7

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	581.1	83.9	2.9 GB	view
4k	583.7	68.9	3.4 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	83.9	1.00×
2×	98.9	1.18×
4×	112.6	1.34×