97 articles
MPT (MosaicML model family)
MPT (MosaicPretrainedTransformer) is a family of open-weight large language models released by MosaicML in 2023, with differing licenses such as Apache 2.0 for MPT-7B Base.
Muse Spark
Muse Spark is a proprietary, natively multimodal large language model developed by Meta Superintelligence Labs and released on April 8, 2026, powering the Meta AI assistant.
Nemotron
Nemotron, also known as NVIDIA Nemotron, is a family of open-weight large language models developed by NVIDIA, positioned for reasoning and agentic AI workloads and published openly on Hugging Face.
Nous Hermes
Nous Hermes is a family of open-weight instruction-tuned and reasoning large language models from Nous Research, first released in 2023 and known for strict adherence to user-supplied system prompts.
OLMo (model family)
OLMo is a family of fully open large language models from the Allen Institute for AI (AI2), first released in February 2024 with weights, training data, and code published.
OpenChat
OpenChat is a series of open-source large language models fine-tuned for conversation, led by Guan Wang. Its compact 7B models run on consumer GPUs and use the C-RLFT training method.
OpenELM
OpenELM is a family of four small open-weight language models released by Apple in April 2024, in 270 million to 3 billion parameter sizes, each with an instruction-tuned variant.
OpenHermes
OpenHermes is a series of open-source instruction-tuned large language models and an instruction dataset created by Teknium, best known for OpenHermes-2.5-Mistral-7B, a Mistral 7B fine-tune released in November 2023.
OpenLLaMA
OpenLLaMA is an open source, Apache 2.0 licensed reproduction of Meta AI's LLaMA language model, developed by OpenLM Research and trained on the open RedPajama dataset.
OPT (Meta model family)
OPT (Open Pre-trained Transformer) is a family of language models released by Meta AI in May 2022, with sizes from 125 million to 175 billion parameters, roughly matching GPT-3.
Phi (small language model family)
Phi is a family of small language models developed by Microsoft, running from Phi-1 through Phi-4, built on curated textbook-quality training data and used on phones, laptops, and Copilot+ PCs.
Phi-3
Phi-3 is a family of open small language models developed by Microsoft, first released in April 2024 with phi-3-mini, a 3.8 billion parameter model rivals said competed with GPT-3.5.
Phi-4
Phi-4 is a 14-billion-parameter large language model released by Microsoft in December 2024, trained mostly on synthetic data to match larger models on math and STEM reasoning.
Poro / Viking (model family)
Poro and Viking are related open-source multilingual large language model families trained on Finland's LUMI supercomputer by SiloGen, TurkuNLP, and HPLT, released in 2024 under Apache 2.0.
Pythia (model family)
Pythia is a suite of 16 open-source language models released by EleutherAI in 2023, ranging from 70M to 12B parameters, with 154 training checkpoints per model for studying how models learn.
Qwen (model family)
Qwen is a family of large language and multimodal models published by Alibaba Group's Qwen Team, first released in 2023 and distributed with open weights.
Qwen (通义千问)
Qwen (通义千问), also known as Tongyi Qianwen, is a family of large language models from Alibaba Cloud, first unveiled in 2023 and spanning dense, multimodal, and open-weight releases.
Qwen licensing shift
The Qwen licensing shift is Alibaba's move of its Qwen AI models from a restrictive custom license to Apache 2.0, beginning in 2024 and partially reversed in 2026.
Qwen3
Qwen3 is a family of open-weight large language models released by Alibaba's Qwen team in April 2025, spanning eight checkpoints from 0.6B to a 235B-parameter flagship under Apache 2.0.
Qwen3.8-Max
Qwen3.8-Max is a large language model released by Alibaba on August 3, 2026, billed as the most powerful model in its Qwen series to date.
QwQ-32B
QwQ-32B is a 32-billion-parameter open-weight reasoning model released by Alibaba's Qwen team on March 6, 2025, trained with reinforcement learning to match DeepSeek-R1's math and coding performance at a fraction of the size.
RoBERTa
RoBERTa is a transformer encoder from Facebook AI, released in 2019, that keeps BERT's architecture but pretrains it with more data and no next-sentence prediction.
s1 (AI model)
s1, also called s1-32B, is an open-source AI reasoning model created in January 2025 by researchers at Stanford University, the University of Washington, and the Allen Institute for AI.
Sarvam (सर्वम्) (model family)
Sarvam (सर्वम्) is a family of large language models for Indian languages built by Bengaluru startup Sarvam AI, beginning with the 2-billion-parameter Sarvam-1 in October 2024.
SEA-LION
SEA-LION (Southeast Asian Languages in One Network) is a family of open large language models built by AI Singapore, first released in December 2023 to serve Southeast Asian languages.
Solar (model family)
Solar is a family of large language models developed by the South Korean AI company Upstage, beginning in 2023 and known for the depth up-scaling technique.
StableLM (model family)
StableLM is a family of open-weight large language models released by Stability AI beginning in April 2023, progressing from 3B and 7B Alpha models to the Stable LM 2 series in 2024 before going dormant.
Step (model family)
Step is a family of large language and multimodal models from the Chinese AI startup StepFun, whose flagship open model Step3 was released under Apache 2.0 in 2025.
Swallow (AI model)
Swallow is a family of open-weight large language models adapted for Japanese, built by Institute of Science Tokyo with AIST through continual pre-training of Llama and Gemma base models.
T5 (language model)
T5 (Text-to-Text Transfer Transformer) is Google's open-source encoder-decoder language model family (60M–11B parameters) that casts every NLP task as text in, text out, trained on the 750 GB C4 corpus; variants include mT5, ByT5, and FLAN-T5.