← Back to community benchmarks

Qwen3.6-35B-A3B-oQ8

M1 Max (32c) · 64 GB · 8bit · 2026-04-29

Performance

1k

tokens

342.9

PP tok/s

47.8

TG tok/s

2987

TTFT (ms)

35.4

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.8.dev3

macOS macOS 26.4

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	342.9	47.8	35.4 GB	current
4k	376.6	47.4	36.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	47.8	1.00×
2×	70.1	1.47×
4×	74.7	1.56×