← Back to community benchmarks

Qwen3.5-27B-Claude-4.6-Opus-Distilled

M3 Ultra (60c) · 96 GB · 6bit · 2026-03-12

Performance

1k

tokens

292.4

PP tok/s

27.6

TG tok/s

3502

TTFT (ms)

22.0

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 96 GB

GPU Cores 60

Software

oMLX v0.2.9

macOS macOS 26.2

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	292.4	27.6	22.0 GB	current
4k	307.5	27.0	22.4 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	27.6	1.00×
2×	39.1	1.42×