← Back to community benchmarks

Qwen3-Coder-Next

M1 Ultra (64c) · 64 GB · 4bit · 2026-04-12

Performance

1k

tokens

630.8

PP tok/s

46.9

TG tok/s

1623

TTFT (ms)

43.1

Peak mem (GB)

Hardware

Chip M1 Ultra (64c)

Memory 64 GB

GPU Cores 64

Software

oMLX v0.3.5.dev1

macOS macOS 15.7.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	630.8	46.9	43.1 GB	current
4k	827.1	45.4	44.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	46.9	1.00×
2×	80.9	1.72×
4×	118.8	2.53×