← Back to community benchmarks

Qwen3.5-35B-A3B-oQ4e

M1 Max (24c) · 64 GB · 4bit · 2026-03-31

Performance

8k

tokens

431.5

PP tok/s

46.4

TG tok/s

18984

TTFT (ms)

21.2

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 64 GB

GPU Cores 24

Software

oMLX v0.3.0

macOS macOS 26.3

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	368.5	53.3	19.9 GB	view
4k	438.4	49.5	20.9 GB	view
8k	431.5	46.4	21.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	53.3	1.00×
2×	74.6	1.40×