← Back to community benchmarks

Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated

M5 Pro (20c) · 48 GB · 4bit · 2026-04-15

Performance

1k

tokens

1,320

PP tok/s

81.6

TG tok/s

776

TTFT (ms)

19.2

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.3.5.dev1

macOS macOS 26.3

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,320	81.6	19.2 GB	current
4k	1,797	70.1	20.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	81.6	1.00×
2×	135.4	1.66×
4×	264.1	3.24×