Jackrong/Qwopus3.6-27B-Coder-MTP-GGUF Image-Text-to-Text β’ 0.5B β’ Updated about 4 hours ago β’ 88
mlx-community/gemma-4-31B-it-qat-mxfp8 Image-Text-to-Text β’ 9B β’ Updated 7 days ago β’ 1.66k β’ 2
view post Post 3940 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
melcheikh/gemma-4-31B-it-qat-NVFP4-Blackwell Text Generation β’ 17B β’ Updated 4 days ago β’ 3.66k β’ 3
JetBrains/Mellum2-12B-A2.5B-Instruct Text Generation β’ 12B β’ Updated about 4 hours ago β’ 990 β’ 64
JetBrains/Mellum2-12B-A2.5B-Thinking Text Generation β’ 12B β’ Updated about 4 hours ago β’ 2.59k β’ 283
GestaltLabs/Ornstein-Hermes-3.6-27B-GGUF Image-Text-to-Text β’ 27B β’ Updated Apr 26 β’ 1.16k β’ 11
AEON-7/Gemma-4-12B-it-AEON-Abliterated-K4-BF16 Text Generation β’ 12B β’ Updated 5 days ago β’ 2.27k β’ 25
jcbtc/qwen3.6-35b-a3b-crown-halo-mtp-dynamic Text Generation β’ 36B β’ Updated 9 days ago β’ 823 β’ 12
GestaltLabs/Ornstein3.6-27B-MTP-NSC-ACE-SABER-GGUF Image-Text-to-Text β’ 27B β’ Updated 29 days ago β’ 4.62k β’ 12