← Back to community benchmarks

Qwen3.6-35B-A3B-TurboQuant

M4 (8c) · 16 GB · 2bit · 2026-04-17

Performance

1k

tokens

334.8

PP tok/s

61.6

TG tok/s

3059

TTFT (ms)

11.1

Peak mem (GB)

Hardware

Chip M4 (8c)

Memory 16 GB

GPU Cores 8

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	334.8	61.6	11.1 GB	current
4k	353.2	56.9	11.9 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	61.6	1.00×
2×	68.4	1.11×
4×	68.6	1.11×