SmolLM2-135M

Developer Antonello F. released Ferrox, a pure-Rust inference engine that runs open LLMs locally on CPU, Apple Metal, or CUDA, achieving performance parity with llama.cpp on an Apple M2 Pro: 26.9 tok/…

NVIDIA Jetson Orin Nano Super 8GB achieves optimal performance at 25W power mode, delivering 43% more tokens per second than 15W and better energy efficiency than MAXN, according to benchmarks of eigh…

A developer demonstrated the differences between foundation, instruct, and chat models using Hugging Face's SmolLM2-135M family in a free Google Colab notebook. By asking the same question to three mo…