← Back to community benchmarks

Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled

M5 Max (40c) · 128 GB · 8bit · 2026-04-15

Performance

1k

tokens

1,903

PP tok/s

58.9

TG tok/s

538

TTFT (ms)

9.9

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.5

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,903	58.9	9.9 GB	current
4k	2,667	56.9	10.6 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	58.9	1.00×
2×	110.0	1.87×
4×	168.0	2.85×