← Back to community benchmarks

Qwen3-Coder-Next-REAP-48B-A3B-oQ3___5

M3 Max (40c) · 64 GB · 3bit · 2026-04-16

Performance

4k

tokens

1,138

PP tok/s

70.6

TG tok/s

3600

TTFT (ms)

24.6

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.5.dev1

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	956.5	70.7	23.7 GB	view
4k	1,138	70.6	24.6 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	70.7	1.00×
2×	119.4	1.69×
4×	167.2	2.36×