← Back to community benchmarks

IQuest-Coder-V1-14B-Thinking-oQ4

M5 (10c) · 32 GB · 4bit · 2026-04-25

Performance

4k

tokens

445.9

PP tok/s

14.6

TG tok/s

9189

TTFT (ms)

9.1

Peak mem (GB)

Hardware

Chip M5 (10c)

Memory 32 GB

GPU Cores 10

Software

oMLX v0.3.7

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	436.6	15.5	8.5 GB	view
4k	445.9	14.6	9.1 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	15.5	1.00×
2×	31.3	2.02×
4×	40.4	2.61×