uzima-imci-135m

uzima-imci-Q8_0

Weights for Uzima — offline WHO IMCI clinical decision support for frontline health workers, built for the Africa Deep Tech Challenge 2026.

Code, report and evaluation harnesses: https://github.com/Lawalgiyath/ADTC-2026

What this is

A 135M-parameter model fine-tuned to read a health worker's description of a sick child and emit structured IMCI findings, in English, Kiswahili or Hausa.

It does not decide anything clinical. In the Uzima application the classification is produced by a deterministic, unit-tested implementation of the WHO IMCI chart; the model handles perception and explanation. That split is the point of the project — a 135M model is good at language and unreliable as a source of medical truth, so it is not used as one.

Why 135M and why Q8_0

Both were chosen by measurement under the challenge's own audit conditions, which compile llama.cpp with every SIMD path disabled:

Q8_0 is 2.4x faster and more accurate here, which inverts the usual reflex: with no vector units, k-quant dequantisation is expensive compute while Q8_0 needs almost none. Details in the repo's REPORT.md §5.4.

Usage

llama-cli -m uzima-imci-Q8_0.gguf -p "A 9-month-old boy has cough for 3 days. \
I counted 56 breaths in one minute and the lower chest wall goes in when he \
breathes in. Classify using IMCI."

The model answers by first writing a FINDINGS: line, then a CHECK: line for any numeric threshold, then the classification — so its reasoning is auditable.

Safety

Not clinically validated. Not for patient care. The guideline corpus is marked needs_clinical_review and the Kiswahili/Hausa clinical strings carry a NEEDS_REVIEW status in the source until a clinician who speaks the language signs them off. Thresholds are the WHO generic chart; IMCI is nationally adapted and the deployment must load its own.

Verification

sha256  00bd94c95b9a4622fb432f340bb2066cb7eec41c2ff30ce021036c5d8bdc2d16
size    144.8 MB

Licence

Apache-2.0. Base model: SmolLM2-135M-Instruct (Apache-2.0).