← Back to community benchmarks

Qwen2.5-Coder-14B-Instruct

M1 Max (32c) · 64 GB · 4bit · 2026-03-09

Performance

4k

tokens

262.9

PP tok/s

30.1

TG tok/s

15579

TTFT (ms)

9.2

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.2.6

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	271.2	34.4	8.5 GB	view
4k	262.9	30.1	9.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	34.4	1.00×
2×	49.4	1.44×
4×	54.0	1.57×