Efficient

Guanaco

The QLoRA demo chatbot that made single-GPU fine-tuning standard

OpenChat

C-RLFT-tuned open 7B that once matched ChatGPT on benchmarks

Phi

Open, efficient small language models from Microsoft Research.

Solar LLM

Upstage's Solar LLMs — Korea's frontier family, now Solar Pro 3

StableLM

Stability AI's dormant open LLM family — no new models since 2024