Author: Danilo Pau
-
nemotron-3-5-lightning on Ollama for EdgeAI Agents
https://ollama.com/blog/nemotron-3-5-lightning
https://ollama.com/blog/nemotron-3-5-lightning 30B only 3B active , context up to 1M, speculative decoding using multi-token prediction . edgeai agents
-
Running a 28.9M parameter LLM on a microcontroller
GitHub – slvDev/esp32-ai · GitHub
This is a 28.9 million parameter language model that generates text on an ESP32-S3 microcontroller. It runs on the chip itself, with nothing sent to a server, and it displays generated text at 9.88 tokens per second on a small screen wired to the chip. It fits because most of the model lives in flash instead of RAM, using Per-Layer Embeddings, an idea from Google’s Gemma 3n.
Thanks to Michael Stauffer
-
Recursive Multi-Agent Systems
RecursiveMAS, a recursive multi-agent framework that casts the
entire system as a unified latent-space recursive computation -
SLMs Survey
A Comprehensive Survey of Small Language Models: Technology, On-Device Applications, Efficiency, Enhancements for LLMs, and Trustworthiness
GitHub – FairyFali/SLMs-Survey: Survey of Small Language Models from Penn State, … · GitHub
Source Michael Stauffer
-
LFM2.5-230M Physical AI
LFM2.5-230M https://www.liquid.ai/blog/lfm2-5-230m on a Unitree G1 https://www.youtube.com/shorts/CuMOWa2y1Ho, running on NVIDIA Jetson Orin. it takes a single natural-language instruction and decomposes it into a sequence of tool calls that invoke pre-trained low-level skills provided by NVIDIA’s SONIC framework
-
Scaling Down is the New Scaling Up
Thanks to Michael Stauffer for providing it