Modelpublic

costinstroie/RoQwen3-VL-2B-Instruct-GGUF

sourceHugging Facecc-by-nc-4.0updated 2mo agoView on Hugging Face

0likes139downloads

Model Card

RoQwen3-VL-2B-Instruct-GGUF (Q4KM + mmproj F16)

GGUF quantization of OpenLLM-Ro/RoQwen3-VL-2B-Instruct, converted with llama.cpp's convert_hf_to_gguf.py. Two files:

—RoQwen3-VL-2B-Instruct-Q4_K_M.gguf — the text/language-model half, Q4KM
—RoQwen3-VL-2B-Instruct-mmproj-F16.gguf — the vision projector (multimodal), F16

Load both together in LM Studio / llama.cpp for image input, or just the text file for text-only use.

Non-commercial (cc-by-nc-4.0, inherited from the base model).