Llama

Alpaca

Stanford's instruction-tuned Llama model — trained on 52k GPT-generated instructions for $600.

Beluga

Top-ranked instruction model from StabilityAI — trained with System Prompt Tuning for superior instruction following.

CodeLlama

Meta's open-source code LLM family — specialised versions for Python, instruction following, and code infill.

Guanaco

QLoRA-fine-tuned open-source chatbot that achieves ChatGPT quality using only 24GB GPU memory.

Koala

Berkeley's open-source chatbot trained on dialogue data from real users — excellent conversational naturalness.

Nous Hermes

Community fine-tuned instruction model from Nous Research — top performer on open-source model leaderboards.

Orca

Microsoft's small language model trained to reason like GPT-4 by learning from complex explanations.

Platypus

Open-source LLM fine-tuned on STEM and logic questions — top benchmark scorer with minimal training data.

Smaug by Abacus

Open-weight fine-tunes from Abacus AI

Vicuna

Fine-tuned open-source chatbot trained on ShareGPT conversations — 90% quality of ChatGPT at minimal cost.

WizardLM

Microsoft's instruction-following LLM trained with Evol-Instruct — progressively harder instructions produce top results.