view article Article Accelerating Qwen3-8B Agent on Intel® Core™ Ultra with Depth-Pruned Draft Models 29 days ago • 18
Granite 4.0 Collection IBM's new Granite-4.0 models! Run Dynamic GGUFs or fine-tune with Unsloth. • 24 items • Updated 25 days ago • 18
Moshi v0.1 Release Collection MLX, Candle & PyTorch model checkpoints released as part of the Moshi release from Kyutai. Run inference via: https://github.com/kyutai-labs/moshi • 15 items • Updated Apr 18 • 239
Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels Paper • 2508.17437 • Published Aug 20 • 36
STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer Paper • 2508.10893 • Published Aug 14 • 31
DINOv3 Collection DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 13 items • Updated Aug 21 • 362
Falcon-H1 Collection Falcon-H1 Family of Hybrid-Head Language Models (Transformer-SSM), including 0.5B, 1.5B, 1.5B-Deep, 3B, 7B, and 34B (pretrained & instruction-tuned). • 38 items • Updated Sep 14 • 56
PaliGemma 2 Release Collection Vision-Language Models available in multiple 3B, 10B and 28B variants. • 32 items • Updated Jul 10 • 150
Phi-3 Collection Phi-3 family of small language and multi-modal models. Language models are available in short- and long-context lengths. • 26 items • Updated May 1 • 574
EXAONE-3.5 Collection EXAONE 3.5 language model series including instruction-tuned models of 2.4B, 7.8B, and 32B • 11 items • Updated Jul 7 • 119
Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion Paper • 2412.04424 • Published Dec 5, 2024 • 63