Local AI Picks
Find open-weight AI models that fit your hardware, with weight sizes, memory and sources.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"localaipicks": {
"url": "https://localaipicks.com/mcp"
}
}
}Remote endpoints
https://localaipicks.com/mcpstreamable-httpWhat it can do
Tool inventory
Tools (4)
🟢list_tasks
The tasks Local AI Picks lists open-weight models for (text LLM, coding, speech to text, text to speech, image, video, music, translation, OCR), with the number of current models and the page for each.
Input Schema
{
"type": "object",
"properties": {}
}🟢find_models(task, memory_gb, device, limit)
Current open-weight models for one task, latest version of each family, in the same order as the site. Give memory_gb (and device) to keep only models whose smallest listed weight option fits; memory is estimated only for text LLMs and taken from vendor sources otherwise, and is "unknown" when neither exists. No ratings and no speed estimates.
Input Schema
{
"type": "object",
"properties": {
"task": {
"type": "string",
"description": "Task id from list_tasks, e.g. \"llm\", \"coding\", \"image\"."
},
"memory_gb": {
"description": "GPU VRAM or unified memory in GB.",
"type": "number",
"exclusiveMinimum": 0,
"maximum": 2048
},
"device": {
"description": "apple counts MLX weights; gpu and cpu do not.",
"type": "string",
"enum": [
"apple",
"gpu",
"cpu"
]
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 30
}
},
"required": [
"task"
]
}🟢get_model(slug)
One model: parameters, license, context length, every listed weight option with file size and memory need, third-party scores with their source and date, whether this site tested it, and links.
Input Schema
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"maxLength": 120,
"description": "Model slug from find_models."
}
},
"required": [
"slug"
]
}🟢compare_models(slugs)
The same facts as get_model for 2 to 4 models side by side.
Input Schema
{
"type": "object",
"properties": {
"slugs": {
"minItems": 2,
"maxItems": 4,
"type": "array",
"items": {
"type": "string",
"maxLength": 120
}
}
},
"required": [
"slugs"
]
}Community
Evidence