← Back to community benchmarks

Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-VLMoQ6

M5 Pro (16c) · 48 GB · 6bit · 2026-05-03

Performance

1k

tokens

1,256

PP tok/s

73.3

TG tok/s

816

TTFT (ms)

27.6

Peak mem (GB)

Hardware

Chip M5 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.3.8rc1

macOS macOS 26.4

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,256	73.3	27.6 GB	current
4k	1,794	70.8	28.4 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	73.3	1.00×
2×	104.1	1.42×
4×	126.7	1.73×