← Back to community benchmarks

Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated

M3 Max (40c) · 128 GB · 8bit · 2026-05-19

Performance

1k

tokens

1,029

PP tok/s

70.5

TG tok/s

995

TTFT (ms)

35.4

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.9rc1

macOS macOS 15.7.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,029	70.5	35.4 GB	current
4k	1,431	67.9	36.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	70.5	1.00×
2×	118.9	1.69×
4×	168.5	2.39×