Gemma 3 QAT Collection Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 8 items • Updated 6 days ago • 107
Rei-12B Collection A small preview of what might become the first(or second?) stepping stone for Magnum v5 • 6 items • Updated 9 days ago • 4
Llama Nemotron Collection Open, Production-ready Enterprise Models • 4 items • Updated 1 day ago • 28
EXAONE-Deep Collection EXAONE reasoning model series of 2.4B, 7.8B, and 32B, optimized for reasoning tasks including math and coding • 9 items • Updated 22 days ago • 86
OLMo 2 Collection Artifacts for the second set of OLMo models. • 27 items • Updated 20 days ago • 108
DeepHermes Collection Preview models of hybrid reasoner Hermes series • 6 items • Updated 27 days ago • 27
Jamba 1.6 Collection The AI21 Jamba family of models are hybrid SSM-Transformer foundation models, outperforming open model competitors on quality and speed. • 2 items • Updated Mar 6 • 13
C4AI Aya Vision Collection Aya Vision is a state-of-the-art family of vision models that brings multimodal capabilities to 23 languages. • 5 items • Updated Mar 4 • 68
Phi-4 Collection Phi-4 family of small language and multi-modal models. • 7 items • Updated Mar 3 • 113
Foundation Text-Generation Models Below 360M Parameters Collection Great candidates for fine-tuning targeting Wllama and Transformers.js for mobile devices, ordered by number of parameters. • 36 items • Updated 2 days ago • 30
Ovis2 Collection Our latest advancement in multi-modal large language models (MLLMs) • 15 items • Updated 15 days ago • 59
SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines Paper • 2502.14739 • Published Feb 20 • 100