# Local AI Picks (localaipicks.com)

Catalogues open-weight AI models by task and device memory, showing memory needs, benchmark scores and sample outputs from its own test runs.

- Atlas card: https://inite.ai/en/atlas/localaipicks.com
- Site: https://localaipicks.com
- For: people who want to run open-weight AI models locally on their own hardware
- Categories: llmops
- Use not measured/100 · alive 100/100

## Used for

- check which open models fit your device's memory
- compare local speech-to-text models by memory needs
- run coding agents on your own machine

## Price

Not read yet.

## For developers

- MCP server: com.localaipicks/localaipicks (namespace; open on 2026-10-29, 4 tools)
- Read 2026-10-29

## MCP server, measured daily

Server: https://localaipicks.com/mcp, checked every day since 2026-10-29 (4 checks).

- Answered: measuring, 4 daily checks so far
- Median first answer: 176 ms
- Sign-in: none
- Context its tool definitions take: about 446 tokens (4 tools)
- Tool definitions: A, 92/100
- Failing "params_described": 2 of 4 tools
- Method: https://inite.ai/en/atlas/mcp/report

## Your data

- Certifications stated: none
- Read 2026-10-29

---

Source: INITE Atlas, https://inite.ai/en/atlas/localaipicks.com. JSON: https://inite.ai/api/atlas/localaipicks.com. MCP: https://inite.ai/api/mcp (atlas_lookup).
