gguf-Q4_K variant is a split native bundle:gliner2-encoder.Q4_K.ggufgliner2-head.Q4_K.ggufmodel.onnx, copied from lion-ai/gliner2-base-v1-onnxmodel.safetensors, copied from fastino/gliner2-base-v1antfly_inference_variants.json and resolves complete encoder/head
pairs as gliner2_split_bundle/v1 at load time.1antfly inference pull antflydb/gliner2-base-v1:gguf:Q4_K
2antfly inference runrecognizeextractclassify