EdgeIMCI Qwen3-0.6B SFT GGUF
Q8_0 GGUF deployment representation of the selected EdgeIMCI structured-extraction fine-tune.
- Base model:
Qwen/Qwen3-0.6B
- Runtime:
llama.cpp
- Quantization:
Q8_0
- Parameters: approximately 0.6B
- GGUF SHA-256:
26d11ee99801455fcef011a3e5ff124b2ff1cce943ed06cbe611c8fbcc42aca2
The model converts primary-healthcare worker descriptions of sick-child findings into a bounded JSON encounter record. It is a provisional research/submission artifact, not a diagnostic system and not authorized for production clinical use.
The retained project evaluation recorded strong structured-extraction performance but also six preregistered clinical-threshold failures. Those limitations remain applicable to this quantized deployment representation.
