Every published setup that reports this GPU, with its models, quantization, runtime and reported results. Use the directory filters below to narrow by capacity, model or runtime.
Capacity is the reported total for this setup. Multi-GPU and unified-memory layouts can behave differently.
A self-built server with 1TB of ECC RAM and a mix of used 3090s and P100s produced internal tools whose economic impact is reported at ten times the hardware cost.
A self-hosted AI ecosystem spans two Linux servers, assigning different GPUs to long-context coding, inference, speech, RAG and media workloads.
Using a gifted 600GB server and a cheap used P100, this owner reports that a capable fully local setup is doable for under $3,000 today.
