Very Large GGUFs Collection GGUF quantized versions of very large models - over 100B parameters • 87 items • Updated 3 days ago • 10
view article Article The Open Source Community is backing OpenEnv for Agentic RL +18 burtenshaw, spisakjo, lysandre, darktex, willcb, qjoy, pawalt, cwing-nv, danielhanchen, andrewzhou, thegovind, shimmyshimmer, Hamid-Nazeri, Sanyam, zkwentz, emre0, lewtun, sergiopaniego, banghua, unseenmars • Jun 8 • 109
RoboBrain-Dex Collection Dexterous VLA utilizing human ego data training • 2 items • Updated Mar 13 • 5
Orca Collection General world foundation model centered on Next-State-Prediction. • 2 items • Updated 19 days ago • 2
GraphVid: Interactive Graph-Controllable Video Generation Paper • 2607.21580 • Published 8 days ago • 8
NVIDIA-labs OO Agents: Native Python Object-Oriented Agents Paper • 2607.20709 • Published 9 days ago • 33
Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction Paper • 2607.20911 • Published 8 days ago • 26
Apertus Mini Collection Distillations and Quantizations of our models into more compact formats (<8B parameters) • 17 items • Updated Jun 24 • 12
Apertus v1 Collection Democratizing Open and Compliant LLMs for Global Language Environments: 8B and 70B open-data open-weights models, multilingual in >1000 languages • 4 items • Updated 7 days ago • 361
ReferTrack: Referring Then Tracking for Embodied Visual Tracking Paper • 2607.20061 • Published 9 days ago • 53
AREX: Towards a Recursively Self-Improving Agent for Deep Research Paper • 2607.21461 • Published 8 days ago • 149
SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Paper • 2607.21553 • Published 8 days ago • 38
Laguna XS.2 Collection Designed for agentic coding and long-horizon work on a local machine. Apache 2.0. • 5 items • Updated Jun 29 • 29
Laguna M.1 Collection Our first M-class coding agent model, designed for long-horizon work. Apache 2.0. • 4 items • Updated 9 days ago • 23
Laguna S 2.1 Collection Our most capable model to date, designed for long-horizon work. • 12 items • Updated 8 days ago • 36
AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents Paper • 2607.18754 • Published 10 days ago • 24