Paddock

Native Rust inference server for open models on NVIDIA GPUs, OpenAI/Anthropic compatible.

PlatformWebfreeglobal

Paddock is a native Rust inference server for running open language models on NVIDIA GPUs, with OpenAI- and Anthropic-compatible APIs, GGUF and safetensors support, and multiple quantization formats, plus a built-in Studio interface. It targets developers self-hosting LLM inference on their own NVIDIA hardware who want broad format support with drop-in API compatibility.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of Paddock - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim Paddock to unlock →

Something wrong with this listing — dead link, not a real product, wrong info?

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether Paddock (or something else) actually fits.

Try a problem