← Back to community benchmarks

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

M5 Pro (20c) · 48 GB · 4bit · 2026-04-05

Performance

4k

tokens

2,209

PP tok/s

96.8

TG tok/s

1854

TTFT (ms)

20.0

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.3.4

macOS macOS 26.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,496	101.1	19.3 GB	view
4k	2,209	96.8	20.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	101.1	1.00×
2×	153.2	1.52×
4×	200.3	1.98×