← Back to community benchmarks

Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled

M1 Max (32c) · 64 GB · 8bit · 2026-04-15

Performance

8k

tokens

597.4

PP tok/s

46.3

TG tok/s

13713

TTFT (ms)

37.3

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.5

macOS macOS 26.2

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	492.4	52.5	36.1 GB	view
4k	595.4	50.6	36.9 GB	view
8k	597.4	46.3	37.3 GB	current