← Back to community benchmarks

Huihui-Qwen3-Next-80B-A3B-Instruct-abliterated

M4 Max (40c) · 128 GB · 4bit · 2026-03-10

Performance

1k

tokens

1,044

PP tok/s

89.2

TG tok/s

981

TTFT (ms)

43.0

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.2.6

macOS macOS 26.4

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,044	89.2	43.0 GB	current
4k	1,300	85.9	43.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	89.2	1.00×
2×	146.3	1.64×
4×	207.9	2.33×