antonellof/ferrox

Pure-Rust GGUF inference engine with quantized CPU, Metal & CUDA kernels, MoE support, OpenAI-compatible server. Benchmarked head-to-head against llama.cpp.

58
Stars
6
Forks
34.5
Radar Score
Rising
Momentum

Scoring Breakdown

Impact11.0
Velocity48.2
Health53.0

Growth Metrics

7-Day Stars
+0
30-Day Stars
+0
Acceleration
x
Language
Rust

Why it ranks

Steady growth — consistently collecting stars and contributors.

Local AITop 72% globally
View on GitHub