Pending benchmarksTracking since Oct 16, 2026
Is LFM2.5-24B-A2B state of the art?Pending benchmarks.Announced Oct 13, 2026; no independent results yet.
Liquid AI's local model for laptops and PCs, built to handle multi-step agent tasks. Instruct and Base checkpoints.
Announced facts
The details so far
- Lab
- Liquid AI
- Announced
- Oct 13, 2026
- API
- Not yet
- Open weights
- Published
- Parameters
- 24B total / 2B active
- Focus
- On-device multi-step agent tasks
- Context
- 131K tokens
- Weights
- Instruct and Base on Hugging Faceunsure · Reported by other posts, not the lab post.
Tags marked unsure are not stated on the lab's own pages.
Next steps
What would let us call it
Verdicts use only independent boards we already track. Two consecutive snapshots are required before any crown.
- Publicly announced with a source
- Usable by the public (API or weights)
- Listed on an independent board we track
- Enough results for a rank in a category
- Holds across two snapshots (crowns only)
Receipts
Sources
LABLiquid AI announcement on Xx.com/liquidai/status/2110055807194931348 · Oct 13, 2026Tracking continues until an independent board lists it.