Qwen3-VL-2B MedQA GGUF
This repository hosts a merged Q4_K_M GGUF export of a MedQA-tuned variant of Qwen/Qwen3-VL-2B-Instruct.
Artifact
Qwen3VL-2B-Instruct-Q4_K_M.gguf: tuned language model export used by the Ambrosia iOS app.
Notes
- This is intended for local inference.
- The matching vision projector remains the upstream
mmproj-Qwen3VL-2B-Instruct-Q8_0.gguffromQwen/Qwen3-VL-2B-Instruct-GGUF. - Validation accuracy during local tuning reached
47.88%on MedQA-USMLE-4-options validation.
- Downloads last month
- 253
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for amankishore/qwen3-vl-2b-medqa-gguf
Base model
Qwen/Qwen3-VL-2B-Instruct