tokenstead.ai
Catalog of open-weight and cloud AI models with benchmarks, local hardware fit checks, API cost estimates and guides for running AI on owned hardware.
First seen 2026-10-12 · Last seen 2026-10-12 · Source: webmcp.com
Answer 5 · Act 0 · Transact 0 · Score: Not yet scored
Tool inspector
find_models_for_hardware
Find which AI models can run locally on given hardware, with a fit verdict and estimated tokens per second. Provide a chip name, or an explicit memory size plus memory type. Same engine as Tokenstead's rig finder.
Input schema
| Property | Type | Required | Description |
|---|---|---|---|
chip_name |
string | no | Chip name, e.g. 'RTX 4090', 'M5 Max', 'Ryzen AI Max+ 395' |
memory_gb |
number | no | Memory available in GB (use with memory_type when no chip_name) |
memory_type |
string | no | Memory type when no chip_name given |
use_case |
string | no | Rank results for this use case |
limit |
number | no | Max results (default 10, max 25) |
Raw JSON schema
{
"type": "object",
"properties": {
"chip_name": {
"type": "string",
"description": "Chip name, e.g. 'RTX 4090', 'M5 Max', 'Ryzen AI Max+ 395'"
},
"memory_gb": {
"type": "number",
"description": "Memory available in GB (use with memory_type when no chip_name)"
},
"memory_type": {
"type": "string",
"enum": [
"unified",
"vram",
"system-ram"
],
"description": "Memory type when no chip_name given"
},
"use_case": {
"type": "string",
"enum": [
"coding",
"reasoning",
"writing",
"chat",
"general",
"vision"
],
"description": "Rank results for this use case"
},
"limit": {
"type": "number",
"description": "Max results (default 10, max 25)"
}
}
}
Similar websites
cesium-browser-agent.pages.dev
Cesium Agent Lab
hunchbank.com
Let visitors get things done without filling out a single form. Hunch turns every form on your site into a tool visitors can run by chatting in plain English. N…
app.voicelogica.ai
Voice Logica
sssnack.com
Agent-made visual feed. Browse, self-register, and publish via MCP or A2A with no connection auth.