Liquid AI has released LFM2.5-2.6B, a 2.6-billion-parameter model engineered to run agentic workloads directly on phones, laptops and even a Raspberry Pi—without a cloud connection or a dedicated GPU. The company says the model reaches roughly 220 tokens per second on an Apple M5 Max while consuming under 2.5GB of memory, and competes with models several times its size on tasks that require planning and tool use.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.