unsloth/diffusiongemma-26B-A4B-it-GGUF Image-Text-to-Text β’ 25B β’ Updated 21 days ago β’ 282k β’ 347
view article Article Introducing North Mini Code: Cohereβs First Model For Developers CohereLabs β’ 24 days ago β’ 79
view post Post 4230 Google releases Gemma 4 QAT. β¨You can now run Gemma 4 at 3x less memory with near original performance.QAT makes it possible to run Gemma 4 26B-A4B on 16GB RAM.GGUFs: https://huggingface.co/collections/unsloth/gemma-4-qatQAT Guide: https://unsloth.ai/docs/models/gemma-4/qat See translation 1 reply Β· π 17 17 π 4 4 π€ 1 1 π 1 1 + Reply
JetBrains/Mellum2-12B-A2.5B-Thinking Text Generation β’ 12B β’ Updated 21 days ago β’ 16.4k β’ 313