Launching today
LLMconfigurator.com
Free tool to check if your GPU can run local LLMs.
5 followers
Free tool to check if your GPU can run local LLMs.
5 followers
Free GPU compatibility checker for local LLMs. Find which models (Llama 4, Gemma 4, DeepSeek V4, Qwen 3.5) your GPU can run. Calculate VRAM usage, compare cloud vs local costs, browse 75+ models, and get setup guides for Ollama, LM Studio, and phones.
honestly really useful tool, saved me a lot of guessing with my 4070. one thing that would be clutch is adding an estimate of inference speed like tokens per second for different quant levels so you know if a model will actually run decently or just technically load
love how straightforward the VRAM calculator is, super useful before pulling the trigger on a new model. one thing that would be clutch is letting users save their GPU setup and get alerts when new models drop that finally fit their hardware, would save a ton of time checking back manually
Would love to see a feature that lets me save my GPU setup and get notified when new models I can actually run get added, since the model list keeps growing faster than I can check it manually.
checked my 4070 against a few models and the vram estimates lined up nicely with what i actually get running ollama. the cloud cost comparison was a nice touch too.