← Back to community benchmarks

Qwen3.6-35B-A3B-Abliterated-Heretic

M5 Max (40c) · 128 GB · 4bit · 2026-04-20

Performance

64k

tokens

2,400

PP tok/s

59.1

TG tok/s

27308

TTFT (ms)

42.1

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,045	97.4	36.4 GB	view
4k	3,569	95.1	37.1 GB	view
64k	2,400	59.1	42.1 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	97.4	1.00×
2×	159.1	1.63×
4×	239.5	2.46×