memra

Rust + CUDA inference engine for serving GGUF models on NVIDIA GPUs.

AI ModelsUnknownOpen source
Visit tool

huggingface.co

About memra

memra is a Rust + CUDA inference engine for serving GGUF models on NVIDIA GPUs. It is optimized for Blackwell (sm_120a), with a separately gated Hopper/H100 (sm_90a) lane.

Description summarised by AI from the sources listed below.

Pricing

Pricing model: Unknown — we have not been able to confirm pricing from the official website, so nothing is stated here.

Pricing summarised by AI from the sources listed below.