LFM2.5-24B-A2B LiquidAI
Status
- Weights
- Providers
- Quants
- Pricing
- Articles
Weights → providers → quants → pricing → articles. A step turns on when the engine observes it; it never turns on from an announcement.
Timeline
- 2026-08-06 · Article: LFM2.5-Encoders for Fast Long-Context Inference on CPU source
- 2026-08-21 · Article: LFM2.5-DSpark: Up to 3.2x Faster Inference from H100 to MacB source
- 2026-10-12 · Weights published on Hugging Face source
- 2026-10-13 · Article: LFM2.5-24B-A2B: Built for fast on-device agents source
- 2026-10-25 · 80 community quantizations on the Hub source
Watch via RSS
Every change to LFM2.5-24B-A2B
- /feeds/models/LiquidAI--LFM2.5-24B-A2B.xml(RSS 2.0) · this model's diffs
- /feeds/drops.xml(RSS 2.0) · all new drops
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.