Skip to content

Liquid AI Nanos (LFM2-1.2B-Extract) as the cognition-role model, a report #8

Description

@mlmrx

The cognition role (memory.extractionModel, ADR-23) lets a small local model own memory-writing while chat uses anything. The shelf recommends LFM2.5-2.6B for it. Liquid also publishes task-specific "Nanos", including LiquidAI/LFM2-1.2B-Extract, tuned for structured extraction, which is exactly the extractor's job.

The experiment: run the extraction prompt in src/memory-extract.js against LFM2-1.2B-Extract, LFM2.5-2.6B, and Qwen3 4B on the same twenty exchanges; report precision (facts that are true and durable), recall (facts a person would have kept), format compliance (does it follow the bullet contract), and speed on CPU. If Extract wins, the shelf entry changes and the guide gets a paragraph; if it does not, the report is still worth having.

Done when: the comparison is posted here with the exchanges used (synthetic, no real data).

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    experimentA spike or a report, not a shipping changeproviderEngines and providers: Ollama, FreeToken, OpenAI-compatible, Anthropic

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions