← Back to community benchmarks

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

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

Performance

4k

tokens

1,797

PP tok/s

70.1

TG tok/s

2279

TTFT (ms)

20.0

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 4,096

Performance by Context Length

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

Batching Results

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