Proprietary generative AI models like ChatGPT are easy to access, but designed in ways that make transparent and responsible use impossible. Widely advertised "open" solutions like Llama are open in weights only, providing no access to training code or to the all-important instruction-tuning data. This guide offers some recommendations for models that can be used in open scholarship and teaching.
Parameter descriptions:
Base Model Data
Are datasources for training the base model comprehensively documented and made available? In case a distinction between base (foundation) and end (user) model is not applicable, this mirrors the end model data entries.
End User Model Data
Are datasources for training the model that the end user interacts with comprehensively documented and made available?
Base Model Weights
Are the weights of the base models made freely available? In case a distinction between base (foundation) and end (user) model is not applicable, this mirrors the end model data entries.
End User Model Weights
Are the weights of the model that the end user interacts with made freely available?
Training Code
Is the source code of dataset processing, model training and tuning comprehensively made available?
Code Documentation
Is the source code of datasource processing, model training and tuning comprehensively documented?
Hardware Architecture
Is the hardware architecture used for datasource processing and model training comprehensively documented?
Preprint
Are archived preprint(s) are available that detail all major parts of the system including datasource processing, model training and tuning steps?
Paper
Are peer-reviewed scientific publications available that detail all major parts of the system including datasource processing, model training and tuning steps?
Modelcard
Is a model card available in standardized format that provides comprehensive insight on model architecture, training, fine-tuning, and evaluation?
Datasheet
Is a datasheet as defined in "Datasheets for Datasets" (Gebru et al. 2021) available?
Package
Is a packaged release of the model available on a software repository (e.g. a Python Package Index, Homebrew)?
API and Meta Prompts
Is an API available that provides unrestricted access to the model (other than security and CDN restrictions)? If applicable, this entry also collects information on the use and availability of meta prompts.
Licenses
Is the project fully covered by Open Source Initiative (OSI)-approved licenses, including all data sources and training pipeline code?
YuLan by Gaoling School of Artificial Intelligence
YuLan-Mini
BLOOMZ by BigScience Workshop
BLOOM
Poro by Silo AI and TurkuNLP and High Performance Language Technologies (HPLT)
Poro-34B
Open Assistant by LAION
Pythia-12B
mT0 by BigScience Workshop
mT5-XXL
Whisper by OpenAI
Whisper-large-v3
Pythia by EleutherAI and Together Computer
Pythia-6.9B
Amber by LLM360
Amber
K2 by LLM360
K2
SmolLM by HuggingFace
SmolLM2-1.7B
OpenChat by OpenChat
Meta-Llama-3-8B
Arabic StableLM by StabilityAI
StableLM-2-1.6B
Instella by AMD
Instella-3B
Dolly by Databricks
Pythia-12B
Tülu by Ai2
Llama-3.1-405B
T5 by Google AI
T5
RedPajama by Together Computer
RedPajama-INCITE-7B-Base
Neo by Multimodal Art Projection
Neo-7B
BERT by Google AI
BERT
AquilaChat by Beijing Academy of Artificial Intelligence
Aquila2-70B-Expr
Eurus by OpenBMB
Mixtral-8x22B-v0.1
DeepSeek V3 by DeepSeek
DeepSeek-V3-Base
Yi by 01.AI
Yi-34B
Teuken by OpenGPT-X
Teuken-7B-base
Salamandra by Barcelona Supercomputing Center
Salamandra-7B
NeuralChat by Intel
Mistral-7B-v0.1
MPT by Databricks
MPT-30B
Lucie by OpenLLM-France
Lucie-7B
GPT-SW3 by AI Sweden
GPT-SW3-6.7B-V2
GPT-NeoXT by Together Computer
GPT-NeoX-20B
Fietje by Bram Vanroy
Phi-2
BTLM by Cerebras
BTLM-3B-8K-Base
Pharia by Aleph Alpha Research
Pharia-1-LLM-7B
minChatGPT by Ethan Yanjia Li
GPT2-Medium
Xwin-LM by Xwin-LM
Llama-2-13B
Vicuna by LMSYS
Vicuna-13B
Phi by Microsoft
Phi-4
OpenELM by Apple
OpenELM-3B
Occiglot by Occiglot
Occiglot-7B-EU5
Mistral by Mistral AI
Mistral-Large-2411
GLM by Zhipu AI
GLM-4-32B-0414
Falcon by Technology Innovation Institute
Falcon3-10B-Base
Minerva by Sapienza Natural Language Processing Group
Minerva-7B-base-v1.0
DeepSeek R1 by DeepSeek
DeepSeek-V3-Base
Zephyr by HuggingFace
Mixtral-8x22B-v0.1
WizardLM by Microsoft and Peking University
LLaMA-7B
InternLM by Shanghai AI Laboratory
InternLM3-8B
CT-LLM by Multimodal Art Projection
CT-LLM-Base
Mistral NeMo by Mistral AI and NVIDIA
Mistral-NeMo-12B-Base
Saul by Equall
Mixtral-8x22B-v0.1
Qwen by Alibaba
Qwen3-235B-A22B-Base
Granite by IBM
Granite-3.3-8B-Base
MiMo by Xiaomi
MiMo-7B-Base
Airoboros by Jon Durbin
Qwen1.5-110B
Starling by NexusFlow
Llama-2-13B
Gemma by Google AI
Gemma-3-27B-PT
Geitje by Bram Vanroy
Mistral-7B-v0.1
BELLE by KE Technologies
Llama-2-13B
Llama 4 by Meta
Llama-4-Maverick-17B-128E
dots.llm1 by RedNote
dots.llm1.base
Marco by Alibaba
Marco-LLM-GLO
Viking by Silo AI and TurkuNLP and High Performance Language Technologies (HPLT)
Viking-33B
Llama 3.1 by Meta
Llama-3.1-405B
OpenMoE by Zheng Zian
OpenMoE-8B
LongAlign by Zhipu AI
Llama-2-13B
UltraLM by OpenBMB
Llama-13B
Command-R by Cohere AI
C4AI-Command-R-V01
Stanford Alpaca by Stanford University CRFM
Llama-7B
StripedHyena by Together Computer
StripedHyena-Hessian-7B
Claire by OpenLLM-France
Falcon-7B
Llama 3.3 by Meta
Llama-3.3-70B
Stable Beluga by StabilityAI
Llama-2-70B
Solar by Upstage AI
Mistral-7B-v0.1
RWKV by BlinkDL/RWKV
RWKV-x070-Pile-1.47B-ctx4096
Persimmon by Adept AI Labs
Persimmon-8B-Base
OPT by Meta
OPT-30B
Nanbeige by Nanbeige LLM lab
Nanbeige2-16B
Jais by G42
Llama-2-70B
Infinity-Instruct by Beijing Academy of Artificial Intelligence
Llama-3.1-70B
H2O-Danube by H2O.ai
H2O-Danube3.1-4B-Chat
FastChat-T5 by LMSYS
Flan-T5-XL
Crystal by LLM360
Crystal
BitNet by Microsoft
BitNet-b1.58-2B4T
Baichuan by Baichuan Intelligent Technology
Baichuan2-13B-Base
StableVicuna by CarperAI
LLaMA-13B
Llama 3 by Meta
Meta-Llama-3-70B
Llama 2 by Meta
Llama-2-70B
Koala by BAIR
Llama-13B
XGen by Salesforce
XGen-Small-9B-Base-R
Hunyuan by Tencent
Hunyuan-A52B-Pretrain
Snowflake Arctic by Snowflake
Snowflake-Arctic-Base
Llama-Sherkala by G42
Llama-3.1-8B
DeepHermes by Nous Research
Llama-3.1-8B
Minimax-Text by Minimax AI
MiniMax-Text-01
Gemma Japanese by Google AI
Gemma-2-2B
One of the most important LLM-related skills students need today is critical AI literacy. Anyone can follow a 10 minute Youtube tutorial on prompt engineering, or read the latest research papers on jailbreaking ChatGPT, Gemini, or similar proprietary models. But for critical AI literacy, more is needed. It should be possible to inspect the training data of a model; to understand how exactly its fine-tuning makes it appear so docile and helpful; and to test prompts and output in easily accessible ways.
The Venn diagrams of truly open models and models with utility in education overlap to a large degree, but not fully. For instance, a model like BloomZ is admirably open on all fronts, but at 175B parameters it can also be prohibitively heavy to deploy in an educational setting. Three models stand out currently for their high degree of openness, exemplary documentation, and ease of access for demonstration purposes: OLMo Instruct by Allen AI, Amber Chat by LLM360, and Pythia Chat by TogetherComputer. All three are small to mid-range models that nonetheless provide the basic behaviour that users have come to expect from instruction-tuned LLMs.
These 7B models are relatively "small" in terms of parameters, but make up for it in terms of openness and accessibility. Running the largest models typically takes a lot of compute, which is why they tend to be provided only through (paid) APIs. Smaller models are easier to deploy in educational and research settings. The three models featured in this guide stand out in terms of the available documentation and code for doing so, as well as in being relatively light weight and easily deployable locally.
There are countless guides online for running LLMs locally using command line tools. Depending on the educational setting and the level of students, this may be all you need. Since command line users are typically savvy enough to figure out their preferred setup, we won't provide instructions here. All three models highlighted here can be easily run through ollama or llama.cpp.
There are also some solutions for educational settings more geared towards point-and-click interfaces. We can recommend LM Studio, available for Mac, Linux and Windows, as a quick way to get you started. LM Studio makes downloading models very easy: you can search for model names, pick the version you want, and download it. After downloading, the model becomes locally available.
LM Studio offers tools for a range of users, from novices to developers. For novices, it will be useful to play with some basic settings like temperature and top n sampling, and to test the effect of different system prompts.