Candle
Minimalist machine learning framework for Rust focused on performance and serverless inference.
About
Candle is a minimalist machine learning framework written in Rust by Hugging Face. It supports CPU, CUDA, and WebAssembly backends and avoids Python overhead for serverless and production inference. The repository ships pre-built implementations of language, vision, audio, and image generation models.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- LLM Inference & Serving
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- License
- Apache-2.0
- Added
- May 7, 2026
Related Tools
Universal LLM deployment engine for native apps on any hardware.
Port of Meta's LLaMA model in C/C++ for efficient CPU inference
Fast serving framework for LLMs with structured generation and RadixAttention.
Fast LLM inference on consumer GPUs using neuron-aware sparse computation.
High-throughput LLM serving engine with PagedAttention
Open-source ChatGPT alternative that runs 100% offline on your computer.