view article Article GGML and llama.cpp join HF to ensure the long-term progress of Local AI +4 Feb 20 β’ 502
Ministral 3 Collection Mistral Ministral 3: new multimodal models in Base, Instruct, and Reasoning variants, available in 3B, 8B, and 14B sizes. β’ 36 items β’ Updated 12 days ago β’ 33
Recommended small models Collection This is everything recent smaller than ~25B parameters that are high quality/reputable β’ 19 items β’ Updated Nov 30, 2024 β’ 179
Unsloth Dynamic 2.0 Quants Collection New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance. β’ 85 items β’ Updated 4 days ago β’ 525
Gemma 3 QAT Collection Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory β’ 15 items β’ Updated Mar 12 β’ 218