Categories / LLM Infrastructure

RustingStudio

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.

Last push 46 minutes ago

anthropic-apicudaggufinferencellama-cppllmlocal-llmmixture-of-expertsmoemtpopenai-apiqwenrustspeculative-decodingvulkan

Created

Oct 2026

Total stars

291

Last 7 days

0

Last 30 days

0

Last 12 months

0

README badge

Rusty Stars badge for RustingStudio/RustingStrata
[![Rusty Stars](https://rustystars.dev/badge/RustingStudio/RustingStrata.svg)](https://rustystars.dev/RustingStudio/RustingStrata)