GitHub · Rust
RustingStudio/RustingStrata
Pure-Rust inference engine for Qwen GGUF models (Qwen3 to Qwen3.8, dense and MoE up to 770B+). CUDA and Vulkan (NVIDIA, AMD), hybrid CPU+GPU experts, MTP speculative decoding, OpenAI and Anthropic compatible server. Up to ~1.7x llama.cpp decode on a 12 GB RTX 3060.
- Stars
- 291
- Forks
- 36
- Stars gained in 24 hours
- +31
- Forks gained in 24 hours
- +4
Topics: anthropic-api, cuda, gguf, inference, llama-cpp, llm, local-llm, mixture-of-experts, moe, mtp
Latest data point: Nov 20, 2026 · 291 stars · 36 forks