← Back to community benchmarks

Qwen3.5-9B-Heretic

M2 (10c) · 16 GB · 4bit · 2026-03-10

Performance

1k

tokens

104.2

PP tok/s

17.5

TG tok/s

9823

TTFT (ms)

5.8

Peak mem (GB)

Hardware

Chip M2 (10c)

Memory 16 GB

GPU Cores 10

Software

oMLX v0.2.6

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	104.2	17.5	5.8 GB	current
4k	102.6	14.3	6.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	17.5	1.00×
2×	7.8	0.45×
4×	7.3	0.42×