rtx-2080

Here is 1 public repository matching this topic...

riccardogiorato / local-ai-RTX-2080

Archive of every local LLM tested on one NVIDIA RTX 2080 8GB (TU104) on Linux — recipes, runtimes, quants, pinned sources, settings, context ceilings, and reproducible measurements. Failures included.

linux docker turing rtx2080 llamacpp llama-cpp local-ai gguf ollama-alternative 8gb-vram rtx-2080

Updated Oct 3, 2026
Cuda

Add this topic to your repo

To associate your repository with the rtx-2080 topic, visit your repo's landing page and select "manage topics."

Learn more