Vetted Consumer
A free, hosted MCP server for local-LLM hardware decisions. Ask whether a model fits your GPU, Mac, or mini-PC, which GGUF quant to download, the cheapest machine that runs it, and the buy-vs-rent-vs-API cost, from a maintained catalog of models and machines plus a monthly used-GPU price feed. No install, no API key. Tools: can_i_run_it, recommend_quant, cheapest_hardware_for_model, recommend_hardware, compare_hardware, cost_compare, get_used_gpu_prices, list_models, list_hardware. Works with Claude, Cursor, Cline, and any MCP client.
How to connect
https://vetted-consumer--hi-10f9.run.tools
tools/list returns the expected tools before relying on them in production.Tools
(9)-
can_i_run_itWill a given local LLM run on given hardware? Returns fit, the best quant that fits, theoretical tok/s, and real owner-measured tok/s where available.
-
recommend_quantWhich GGUF quantization to download for a model on given hardware: the full quant ladder with file size, max context, and tok/s for each, plus the recommended pick.
-
cheapest_hardware_for_modelThe cheapest catalogued, buyable machine that runs a given model at Q4 with the requested context.
-
list_modelsList the local LLM model classes the tools know about (params, dense/MoE, native context).
-
list_hardwareList the machines the tools know about (memory, bandwidth, price, buy link).
-
cost_compareBuy vs rent vs API cost to run a model locally: monthly/1y/3y totals, break-even months, and the energy cost per 1M tokens. Same math as /cost-calculator/.
-
recommend_hardwareRanked list of catalogued, buyable machines that run a model at the requested context, cheapest first, with an optional budget cap.
-
get_used_gpu_pricesCurrent typical used-GPU prices for local-AI rigs (eBay Browse API median asking + hand-verified, monthly).
-
compare_hardwareSide-by-side memory, bandwidth, price, and (with a model) fit + tok/s for 2 to 4 machines.