Categories
AI News

Inkling 2 Mini Runs Half Its Layers Three Times, and Fits on a Laptop

Thinking Machines’ open 26.4B Inkling 2 Mini loops 12 of its 24 layers three times per token and fits in about 20GB. Most scores are self-reported.

Categories
AI News

A 180B Open Model on a 32GB Laptop, by Leaving Most of It on Disk

A Hugging Face post runs a 180B open MoE model on a 32GB MacBook by streaming experts from the SSD. It’s about 6% behind a rival engine.

Categories
AI News

llama.cpp Hits 1.0, and Promises to Stop Breaking Your Code

llama.cpp, the engine behind much local AI, reached 1.0. The real news isn’t speed but a promise: its API won’t break without warning.

Categories
AI News

Zyphra’s Open Voice Cloner Fits on a Phone. Its Docs Skip Consent

Zyphra’s open ZONOS3-Mini clones a voice from a clip of up to 60 seconds, in 43 languages, on a phone. Its docs say nothing about consent.

Categories
iRaluca

Tether’s 0.8B BotPsy Runs Agents on Your Phone, but Not With Your Money

Tether’s open 0.8B BotPsy calls tools on-device and doubles its base model’s agent scores. Its makers say: keep it from money. Scores are self-reported.

Categories
AI News iRaluca

Liquid AI’s LFM3 Grows Six Small Specialists From One 1.7B Trunk

Liquid AI’s open-weight LFM3: six ~2B models for text, vision, audio and decisions, grown from one base. The scores are self-reported.

Categories
AI News

Recursive’s Flint Is an Open Coding Model Partly Designed by Another AI

Recursive’s open-weight Flint codes on a 48GB laptop, and its makers say an AI research system helped design it. The scores are self-reported.

Categories
AI News iRaluca

Nvidia’s Bolt Fits a 74B Model in 24GB by Shrinking Its Experts to 2 Bits

Nvidia’s open Nemotron 3.5 Bolt squeezes a 120B parent into 74B parameters and 24GB, with 2-bit experts. What the model card shows, and what it skips.

Categories
AI News iRaluca

Liquid AI’s New Agent Model Is 24B, but Only 2B Show Up for Work

Liquid AI’s open-weight LFM2.5-24B-A2B runs agents on laptops with 2B active parameters. Strong at tools, weaker on facts, by its own admission.

Categories
AI News iRaluca

Liquid AI’s d1 Answers Questions About Pictures Without Writing a Word

Liquid AI’s open-weight d1 models answer yes/no, pick-one and score questions about text, images and speech in one pass, without writing text.