Skip to content
TechIndexSubmit
Back to directory

Saber Engine

A high-performance inference engine built in Rust, supporting models like Qwen 3.8 27b and Flash next. It achieves high token per second rates for LLM serving.

Similar tools

  • A pure-Rust GGUF inference engine with CUDA and Vulkan backends, designed for efficient local execution of large AI models like DeepSeek-V4.1-Flash.

    Dev Tools
  • AI inference engine supporting local image editing and generation using Qwen Image 2.1 Turbo and LoRA models.

    Dev Tools
  • A high-throughput and memory-efficient inference and serving engine for LLMs

    Models
  • A high-performance inference engine designed for Jev-like decision models, offering significant speedups over existing solutions. It supports over 30 popular local decision models for AI developers.

    Dev Tools
  • Highly Performant, Modular, Memory Safe and Production-ready Inference, Ingestion and Indexing built in Rust 🦀

    AI Apps
  • MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.

    Models