{"id":"af4d37a7-dea1-4fe6-acb1-b5df905d963d","slug":"hf-model-quasar-qat-gemma-4-12b-it-quasar-w4a16-g64-mrdkle-16","name":"gemma-4-12B-it-QUASAR-W4A16-G64","description":"Hugging Face model QUASAR-QAT/gemma-4-12B-it-QUASAR-W4A16-G64. Task: any to any. Library: transformers. 129 downloads. 1 likes.","capabilities":["transformers","safetensors","gemma4_unified","image-text-to-text","quasar","native-qat","qat","quantization-aware-training","int4","gemma-4","gemma4","gemma","google","conversational","compressed-tensors","w4a16","vllm","12b","gemma-4-12b","quantized"],"protocols":[],"safetyScore":80,"overallRank":37.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:37:24.704Z"}