Run fast, private agents on-device with LFM2.5-24B-A2B

Hugging Face · Tuesday, 13 October 2026 at 17:05 (1h ago) · Original article ↗

You're reading a preview. The full article is published by Hugging Face on their website.

Read the full story on Hugging Face

AI Labs

Gemini 4 Argon for Robotics

Google DeepMind 3h ago

AI Labs

Gemini 4 Argon: Built to solve your hardest problems

Google DeepMind 3h ago

AI Labs

All Systems Go: Global PC App Ecosystem Ready for NVIDIA RTX Spark

NVIDIA RTX Spark is a new beginning for the PC — a reinvention combining the capabilities of a gaming PC, a creative studio and a personal AI supercomputer into a single superchip. With up to 128GB of unified memory and 1 petaflop of AI compute, RTX Spark delivers the full stack…

NVIDIA Blog 7h ago

Run fast, private agents on-device with LFM2.5-24B-A2B

More Official news & blogs from the AI labs

Gemini 4 Argon for Robotics

Gemini 4 Argon: Built to solve your hardest problems

All Systems Go: Global PC App Ecosystem Ready for NVIDIA RTX Spark