Repository
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
297
Today
+7
last 24 hours
This week
+69
Forks
37
Clone
git clone https://github.com/RustingStudio/RustingStrata.gitStar growth
- Created
- 2026-10-10
- Last commit
- 2026-11-13
- Gained since tracking
- +214
Updated Fri, 20 Nov 2026 07:21:13 GMT · description from the project itself