Model Memory Utility is a web application that helps users estimate the GPU VRAM needed to run models from the Hugging Face Hub. Users input a model name or URL, select library and precision, and receive memory usage estimates, aiding ML engineers and researchers in resource planning.
In the LLM eval & observability space, Model Memory Utility takes a focused approach. It focuses on estimating GPU memory requirements for running machine learning models efficiently. Model Memory Utility is a B2B product aimed at machine learning engineers and researchers. Model Memory Utility is free to use. The product ships for the web, and it can be self-hosted.
It is developed by hf-accelerate, and the product first shipped in 2023. Across PulseGate's embedding index, Model Memory Utility has few near neighbours, marking it as relatively distinct. Among its 5 catalogued features are VRAM estimation, model selection, and precision options.
Latest indexed changes and source events
hf-accelerate/model-memory-usage discovered by the PulseGate indexer
Other apps tracked under the same category.
