io.github.TheBaronofAI/vetted-consumer

Official9 tools

Will a local LLM run on your hardware? GGUF quant, buy-vs-rent-vs-API cost, used-GPU prices.

Analyzes local LLM compatibility, cost comparison and used GPU pricing for hardware.

Captured live from the server via tools/list.

can_i_run_it

Will 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.

Parameters (10)

modelstring
Model name, e.g. 'Llama 70B', 'gpt-oss-120B', 'Qwen 32B'. Use list_models to see known names.
total_bnumber
For an unlisted model: total parameters in billions
active_bnumber
For an unlisted model: active params in billions (= total for dense, less for MoE)
mxfp4boolean
True if the model ships natively in MXFP4 (e.g. gpt-oss)
hardwarestring
Hardware name/id, e.g. 'rtx-3090', 'Mac 128GB', 'Strix Halo'. Use list_hardware to see known ones.
vram_gbnumber
For custom hardware: VRAM or unified memory in GB
bandwidth_gbpsnumber
For custom hardware: memory bandwidth in GB/s
unifiedboolean
True for unified-memory machines (Macs, Strix Halo, CPU+RAM)
contextnumber
Context window in tokens (default 8192)
kv_precisionstring
KV cache precision (default f16)

recommend_quant

Which 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.

Parameters (10)

modelstring
Model name, e.g. 'Llama 70B', 'gpt-oss-120B', 'Qwen 32B'. Use list_models to see known names.
total_bnumber
For an unlisted model: total parameters in billions
active_bnumber
For an unlisted model: active params in billions (= total for dense, less for MoE)
mxfp4boolean
True if the model ships natively in MXFP4 (e.g. gpt-oss)
hardwarestring
Hardware name/id, e.g. 'rtx-3090', 'Mac 128GB', 'Strix Halo'. Use list_hardware to see known ones.
vram_gbnumber
For custom hardware: VRAM or unified memory in GB
bandwidth_gbpsnumber
For custom hardware: memory bandwidth in GB/s
unifiedboolean
True for unified-memory machines (Macs, Strix Halo, CPU+RAM)
contextnumber
Context window in tokens (default 8192)
kv_precisionstring
KV cache precision (default f16)

cheapest_hardware_for_model

The cheapest catalogued, buyable machine that runs a given model at Q4 with the requested context.

Parameters (5)

modelstring
Model name, e.g. 'Llama 70B', 'gpt-oss-120B', 'Qwen 32B'. Use list_models to see known names.
total_bnumber
For an unlisted model: total parameters in billions
active_bnumber
For an unlisted model: active params in billions (= total for dense, less for MoE)
mxfp4boolean
True if the model ships natively in MXFP4 (e.g. gpt-oss)
contextnumber
Context window in tokens (default 8192)

list_models

List the local LLM model classes the tools know about (params, dense/MoE, native context).

No parameters.

list_hardware

List the machines the tools know about (memory, bandwidth, price, buy link).

No parameters.

cost_compare

Buy 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/.

Parameters (8)

hardwarestring
Catalogued hardware name/id (see list_hardware), e.g. 'rtx-3090-used'
price_usdnumber
For custom hardware: price in USD
tdp_wnumber
For custom hardware: board power draw in watts
hoursnumber
Active hours per day (default 3)
tokensnumber
Tokens generated per day, for the API comparison (default 300000)
kwhnumber
Electricity $/kWh (default 0.16)
rentnumber
Cloud GPU $/hour (default 0.59)
apinumber
API $/million tokens (default 1.0)

recommend_hardware

Ranked list of catalogued, buyable machines that run a model at the requested context, cheapest first, with an optional budget cap.

Parameters (7)

modelstring
Model name, e.g. 'Llama 70B', 'gpt-oss-120B', 'Qwen 32B'. Use list_models to see known names.
total_bnumber
For an unlisted model: total parameters in billions
active_bnumber
For an unlisted model: active params in billions (= total for dense, less for MoE)
mxfp4boolean
True if the model ships natively in MXFP4 (e.g. gpt-oss)
contextnumber
Context window in tokens (default 8192)
kv_precisionstring
KV cache precision (default f16)
budgetnumber
Optional max price in USD

get_used_gpu_prices

Current typical used-GPU prices for local-AI rigs (eBay Browse API median asking + hand-verified, monthly).

Parameters (1)

gpustring
Optional name/id filter, e.g. "3090"

compare_hardware

Side-by-side memory, bandwidth, price, and (with a model) fit + tok/s for 2 to 4 machines.

Parameters (7)

hardwarestringrequired
2 to 4 hardware names/ids, comma-separated
modelstring
Model name, e.g. 'Llama 70B', 'gpt-oss-120B', 'Qwen 32B'. Use list_models to see known names.
total_bnumber
For an unlisted model: total parameters in billions
active_bnumber
For an unlisted model: active params in billions (= total for dense, less for MoE)
mxfp4boolean
True if the model ships natively in MXFP4 (e.g. gpt-oss)
contextnumber
Context window in tokens (default 8192)
kv_precisionstring
KV cache precision (default f16)

Install

claude_desktop_config.json

{
  "mcpServers": {
    "vetted-consumer": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://vettedconsumer.com/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.