Jeriel’sTechnology RadarMain Site

huggingface.co

Hermes 3 Llama 3.2 3B

A Nous Research instruction-tuned model based on Llama 3.2 3B.

https://huggingface.co/NousResearch/Hermes-3-Llama-3.2-3B

About This Resource

A Nous Research instruction-tuned model based on Llama 3.2 3B. Its model page provides weights, formatting guidance, and information about its intended conversational and tool-use behavior.

Next

Colibri

Models & Inference

An inference project that streams mixture-of-experts model weights from storage to work within limited memory.

Saved github.comrepository

Slotstream

Models & Inference

An experimental inference tool for running mixture-of-experts language models on Macs by streaming expert weights from SSD storage.

Saved github.comrepository