← Back to community benchmarks

Qwen3.5-0.8B9bit

M3 Ultra (60c) · 96 GB · 8bit · 2026-03-09

Performance

1k

tokens

2,884

PP tok/s

302.3

TG tok/s

355

TTFT (ms)

1.9

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 96 GB

GPU Cores 60

Software

oMLX v0.2.6

macOS macOS 26.3.1

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	302.3	1.00×
2×	507.1	1.68×
4×	730.8	2.42×