freriadoc /

Avalon

Fast fork of llama.cpp designed for Qwen3.8-Flash-Next

#2 in Local LLMs C++ 330 stars

Updated 37 min ago

View on GitHub

Why now

+260 stars gained this week

Stars gained each day, last 30 days

Oct 9Oct 24 Nov 7

This week Before

In short

The README covers the performance numbers on an AMD RX 7900 XT in detail, and explains how the expert cache is managed between VRAM and system RAM. It does not say how to install or launch the server.

Summary written by AI from the repository’s description and README.

Awards

Add any of these badges to your README.

#2 Riser Of The Week in Local LLMs
Reached on November 6, 2026
#9 Riser Of The Week in LLM
Reached on November 2, 2026

More badge styles

These follow this week’s figures, updated every hour.

This week card
This week badge

freriadoc / Avalon