← Back to community benchmarks

Huihui-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliterated

M2 Max (30c) · 64 GB · 4bit · 2026-07-14

Performance

1k

tokens

591.9

PP tok/s

72.8

TG tok/s

1730

TTFT (ms)

19.3

Peak mem (GB)

Hardware

Chip M2 Max (30c)

Memory 64 GB

GPU Cores 30

Software

oMLX v0.5.1

macOS macOS 26.5.2

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	591.9	72.8	19.3 GB	current
64k	291.4	37.8	21.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	72.8	1.00×
2×	88.5	1.22×