← Back to community benchmarks

Qwen3.5-35B-A3B

M3 Ultra (60c) · 96 GB · unknown · 2026-03-10

Performance

1k

tokens

141.4

PP tok/s

0.5

TG tok/s

7240

TTFT (ms)

69.7

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 96 GB

GPU Cores 60

Software

oMLX v0.2.6

macOS macOS 15.3

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	0.5	1.00×
2×	0.9	1.80×