Vetted Consumer

Working · 2.4 s

io.github.TheBaronofAI/vetted-consumerv1.0.0

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

Developer Tools

Website Registry entry

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

https://vettedconsumer.com/mcp

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

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.

modelstring

Model name, e.g. 'Llama 70B', 'gpt-oss-120B', 'Qwen 32B'. Use list_models to see known names.

mxfp4boolean

True if the model ships natively in MXFP4 (e.g. gpt-oss)

contextnumber

Context window in tokens (default 8192)

total_bnumber

For an unlisted model: total parameters in billions

unifiedboolean

True for unified-memory machines (Macs, Strix Halo, CPU+RAM)

vram_gbnumber

For custom hardware: VRAM or unified memory in GB

active_bnumber

For an unlisted model: active params in billions (= total for dense, less for MoE)

hardwarestring

Hardware name/id, e.g. 'rtx-3090', 'Mac 128GB', 'Strix Halo'. Use list_hardware to see known ones.

kv_precisionstring

KV cache precision (default f16)

bandwidth_gbpsnumber

For custom hardware: memory bandwidth in GB/s

This tool isn't marked read-only, so it may change something on the server or in an account you connected.

I understand, run it anyway

Tools (9)

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.

Argument	Type	Description
model	string	Model name, e.g. 'Llama 70B', 'gpt-oss-120B', 'Qwen 32B'. Use list_models to see known names.
mxfp4	boolean	True if the model ships natively in MXFP4 (e.g. gpt-oss)
context	number	Context window in tokens (default 8192)
total_b	number	For an unlisted model: total parameters in billions
unified	boolean	True for unified-memory machines (Macs, Strix Halo, CPU+RAM)
vram_gb	number	For custom hardware: VRAM or unified memory in GB
active_b	number	For an unlisted model: active params in billions (= total for dense, less for MoE)
hardware	string	Hardware name/id, e.g. 'rtx-3090', 'Mac 128GB', 'Strix Halo'. Use list_hardware to see known ones.
kv_precision	string	KV cache precision (default f16)
bandwidth_gbps	number	For custom hardware: memory bandwidth in GB/s

Input schema (JSON)

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "model": {
      "type": "string",
      "description": "Model name, e.g. 'Llama 70B', 'gpt-oss-120B', 'Qwen 32B'. Use list_models to see known names."
    },
    "mxfp4": {
      "type": "boolean",
      "description": "True if the model ships natively in MXFP4 (e.g. gpt-oss)"
    },
    "context": {
      "type": "number",
      "description": "Context window in tokens (default 8192)"
    },
    "total_b": {
      "type": "number",
      "description": "For an unlisted model: total parameters in billions"
    },
    "unified": {
      "type": "boolean",
      "description": "True for unified-memory machines (Macs, Strix Halo, CPU+RAM)"
    },
    "vram_gb": {
      "type": "number",
      "description": "For custom hardware: VRAM or unified memory in GB"
    },
    "active_b": {
      "type": "number",
      "description": "For an unlisted model: active params in billions (= total for dense, less for MoE)"
    },
    "hardware": {
      "type": "string",
      "description": "Hardware name/id, e.g. 'rtx-3090', 'Mac 128GB', 'Strix Halo'. Use list_hardware to see known ones."
    },
    "kv_precision": {
      "enum": [
        "f16",
        "q8",
        "q4"
      ],
      "type": "string",
      "description": "KV cache precision (default f16)"
    },
    "bandwidth_gbps": {
      "type": "number",
      "description": "For custom hardware: memory bandwidth in GB/s"
    }
  },
  "additionalProperties": false
}

cheapest_hardware_for_model

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

Argument	Type	Description
model	string	Model name, e.g. 'Llama 70B', 'gpt-oss-120B', 'Qwen 32B'. Use list_models to see known names.
mxfp4	boolean	True if the model ships natively in MXFP4 (e.g. gpt-oss)
context	number	Context window in tokens (default 8192)
total_b	number	For an unlisted model: total parameters in billions
active_b	number	For an unlisted model: active params in billions (= total for dense, less for MoE)

Input schema (JSON)

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "model": {
      "type": "string",
      "description": "Model name, e.g. 'Llama 70B', 'gpt-oss-120B', 'Qwen 32B'. Use list_models to see known names."
    },
    "mxfp4": {
      "type": "boolean",
      "description": "True if the model ships natively in MXFP4 (e.g. gpt-oss)"
    },
    "context": {
      "type": "number",
      "description": "Context window in tokens (default 8192)"
    },
    "total_b": {
      "type": "number",
      "description": "For an unlisted model: total parameters in billions"
    },
    "active_b": {
      "type": "number",
      "description": "For an unlisted model: active params in billions (= total for dense, less for MoE)"
    }
  },
  "additionalProperties": false
}

compare_hardware

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

Argument	Type	Description
model	string	Model name, e.g. 'Llama 70B', 'gpt-oss-120B', 'Qwen 32B'. Use list_models to see known names.
mxfp4	boolean	True if the model ships natively in MXFP4 (e.g. gpt-oss)
context	number	Context window in tokens (default 8192)
total_b	number	For an unlisted model: total parameters in billions
active_b	number	For an unlisted model: active params in billions (= total for dense, less for MoE)
hardware*	string	2 to 4 hardware names/ids, comma-separated
kv_precision	string	KV cache precision (default f16)

Input schema (JSON)

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "hardware"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "Model name, e.g. 'Llama 70B', 'gpt-oss-120B', 'Qwen 32B'. Use list_models to see known names."
    },
    "mxfp4": {
      "type": "boolean",
      "description": "True if the model ships natively in MXFP4 (e.g. gpt-oss)"
    },
    "context": {
      "type": "number",
      "description": "Context window in tokens (default 8192)"
    },
    "total_b": {
      "type": "number",
      "description": "For an unlisted model: total parameters in billions"
    },
    "active_b": {
      "type": "number",
      "description": "For an unlisted model: active params in billions (= total for dense, less for MoE)"
    },
    "hardware": {
      "type": "string",
      "description": "2 to 4 hardware names/ids, comma-separated"
    },
    "kv_precision": {
      "enum": [
        "f16",
        "q8",
        "q4"
      ],
      "type": "string",
      "description": "KV cache precision (default f16)"
    }
  },
  "additionalProperties": false
}

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/.

Argument	Type	Description
api	number	API $/million tokens (default 1.0)
kwh	number	Electricity $/kWh (default 0.16)
rent	number	Cloud GPU $/hour (default 0.59)
hours	number	Active hours per day (default 3)
tdp_w	number	For custom hardware: board power draw in watts
tokens	number	Tokens generated per day, for the API comparison (default 300000)
hardware	string	Catalogued hardware name/id (see list_hardware), e.g. 'rtx-3090-used'
price_usd	number	For custom hardware: price in USD

Input schema (JSON)

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "api": {
      "type": "number",
      "description": "API $/million tokens (default 1.0)"
    },
    "kwh": {
      "type": "number",
      "description": "Electricity $/kWh (default 0.16)"
    },
    "rent": {
      "type": "number",
      "description": "Cloud GPU $/hour (default 0.59)"
    },
    "hours": {
      "type": "number",
      "description": "Active hours per day (default 3)"
    },
    "tdp_w": {
      "type": "number",
      "description": "For custom hardware: board power draw in watts"
    },
    "tokens": {
      "type": "number",
      "description": "Tokens generated per day, for the API comparison (default 300000)"
    },
    "hardware": {
      "type": "string",
      "description": "Catalogued hardware name/id (see list_hardware), e.g. 'rtx-3090-used'"
    },
    "price_usd": {
      "type": "number",
      "description": "For custom hardware: price in USD"
    }
  },
  "additionalProperties": false
}

get_used_gpu_prices

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

Argument	Type	Description
gpu	string	Optional name/id filter, e.g. "3090"

Input schema (JSON)

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "gpu": {
      "type": "string",
      "description": "Optional name/id filter, e.g. \"3090\""
    }
  },
  "additionalProperties": false
}

list_hardware

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

No arguments.

Input schema (JSON)

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}

list_models

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

No arguments.

Input schema (JSON)

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}

recommend_hardware

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

Argument	Type	Description
model	string	Model name, e.g. 'Llama 70B', 'gpt-oss-120B', 'Qwen 32B'. Use list_models to see known names.
mxfp4	boolean	True if the model ships natively in MXFP4 (e.g. gpt-oss)
budget	number	Optional max price in USD
context	number	Context window in tokens (default 8192)
total_b	number	For an unlisted model: total parameters in billions
active_b	number	For an unlisted model: active params in billions (= total for dense, less for MoE)
kv_precision	string	KV cache precision (default f16)

Input schema (JSON)

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "model": {
      "type": "string",
      "description": "Model name, e.g. 'Llama 70B', 'gpt-oss-120B', 'Qwen 32B'. Use list_models to see known names."
    },
    "mxfp4": {
      "type": "boolean",
      "description": "True if the model ships natively in MXFP4 (e.g. gpt-oss)"
    },
    "budget": {
      "type": "number",
      "description": "Optional max price in USD"
    },
    "context": {
      "type": "number",
      "description": "Context window in tokens (default 8192)"
    },
    "total_b": {
      "type": "number",
      "description": "For an unlisted model: total parameters in billions"
    },
    "active_b": {
      "type": "number",
      "description": "For an unlisted model: active params in billions (= total for dense, less for MoE)"
    },
    "kv_precision": {
      "enum": [
        "f16",
        "q8",
        "q4"
      ],
      "type": "string",
      "description": "KV cache precision (default f16)"
    }
  },
  "additionalProperties": false
}

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.

Argument	Type	Description
model	string	Model name, e.g. 'Llama 70B', 'gpt-oss-120B', 'Qwen 32B'. Use list_models to see known names.
mxfp4	boolean	True if the model ships natively in MXFP4 (e.g. gpt-oss)
context	number	Context window in tokens (default 8192)
total_b	number	For an unlisted model: total parameters in billions
unified	boolean	True for unified-memory machines (Macs, Strix Halo, CPU+RAM)
vram_gb	number	For custom hardware: VRAM or unified memory in GB
active_b	number	For an unlisted model: active params in billions (= total for dense, less for MoE)
hardware	string	Hardware name/id, e.g. 'rtx-3090', 'Mac 128GB', 'Strix Halo'. Use list_hardware to see known ones.
kv_precision	string	KV cache precision (default f16)