← Back to community benchmarks

Qwen3.5-35B-A3B-Hereticmxfp8

M1 Ultra (64c) · 64 GB · 8bit · 2026-03-12

Performance

1k

tokens

747.8

PP tok/s

53.7

TG tok/s

1369

TTFT (ms)

34.9

Peak mem (GB)

Hardware

Chip M1 Ultra (64c)

Memory 64 GB

GPU Cores 64

Software

oMLX v0.2.9

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	747.8	53.7	34.9 GB	current
4k	1,030	52.7	35.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	53.7	1.00×
2×	91.0	1.69×
4×	129.0	2.40×