← Back to community benchmarks

Qwen3.6-35B-A3B-uncensored-heretic

M2 Ultra (60c) · 64 GB · 8bit · 2026-05-03

Performance

4k

tokens

1,116

PP tok/s

53.9

TG tok/s

3671

TTFT (ms)

37.4

Peak mem (GB)

Hardware

Chip M2 Ultra (60c)

Memory 64 GB

GPU Cores 60

Software

oMLX v0.3.8

macOS macOS 15.7.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	839.4	26.1	37.3 GB	view
4k	1,116	53.9	37.4 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	26.1	1.00×
2×	122.6	4.70×
4×	180.2	6.90×