Ferrumox

Popular repositories Loading

1. fox fox Public

   High-performance LLM inference engine — drop-in replacement for Ollama with faster multi-turn inference, lower TTFT, and higher throughput through prefix caching and continuous batching.

   Rust 185 28

2. rabbit rabbit Public

   Run Kimi K3 (2.8T MoE) on a 128GB-RAM consumer machine in pure Rust, experts streamed from disk. Tiny engine, immense model.

   Rust 121 15

3. ferrumox.com ferrumox.com Public

   HTML