#17 today

sudoingX/qwen38-mtp

Python AI Apache-2.0

One llama.cpp flag unlocks +33-39% decode speed for Qwen3.8-27B on consumer GPUs. The MTP head already ships inside your GGUF. Recipe, paired benchmarks, probe tool.

Last active today Created Aug 14, 2026

Stars: 14
Today: +14
Forks: 2
Quality: 93/100
Momentum: 20

First trending

Aug 15, 2026

first spotted on the list

Best rank

#17

highest position reached

Appearances

times on the trending list

Quality score

out of 100

Momentum

trend strength indicator

Star velocity

stars per day since creation

Activity — last 60 days

daily counts, collected every 6 hours

Stars
Forks
Merged PRs
Issues
Closed issues

Collecting activity data since launch — check back in a few days.

Star history

total stars per snapshot

Rank history

position on trending · lower is better

Top contributors

by commits

1 sudoingX 1 commits

Language breakdown

by bytes of code

Python 85.5%

Python 2 KB 85.5%
Shell 386 B 14.5%

Stars badge

Show current stars in your README or profile. Auto-updates every 6 hours.

Markdown

[![sudoingX/qwen38-mtp](https://www.notionpulse.cc/api/badge/sudoingX/qwen38-mtp.svg)](https://www.notionpulse.cc/repo/sudoingX/qwen38-mtp)

HTML

<a href="https://www.notionpulse.cc/repo/sudoingX/qwen38-mtp"><img src="https://www.notionpulse.cc/api/badge/sudoingX/qwen38-mtp.svg" alt="sudoingX/qwen38-mtp stars badge" /></a>

sudoingX/qwen38-mtp

Activity — last 60 days

Star history

Rank history

Top contributors

Language breakdown

Stars badge

Repository of the Day

Repository of the Week

Repository of the Month

Popular in Python

Related repos