← Back to community benchmarks

Qwen3.6-35B-A3B

M3 Max (30c) · 36 GB · 4bit · 2026-04-16

Performance

64k

tokens

673.9

PP tok/s

31.6

TG tok/s

97256

TTFT (ms)

25.0

Peak mem (GB)

Hardware

Chip M3 Max (30c)

Memory 36 GB

GPU Cores 30

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	895.5	88.8	19.3 GB	view
4k	1,104	83.7	20.0 GB	view
64k	673.9	31.6	25.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	88.8	1.00×
2×	137.2	1.55×
4×	176.9	1.99×