AI Resources
InkubaLM vs SERENGETI
A verified, side-by-side comparison. Both records are status-checked by Findra, so you are comparing what each actually offers today, not a stale listing.
Category
AI Resources
AI Resources
Type
LLM
LLM
Country
🇿🇦 South Africa
🌍 Pan-African
Docs status
Docs live
Docs live
Licensing
Institutional only
Pricing
Free / open weights (CC BY-NC 4.0)
Free for research; commercial use requires contacting authors
Verified
Verified
Verified
Last verified
24 Jun 2026
24 Jun 2026
Tags
nlp, llm, african-languages, open-weights, low-resource
nlp, masked-language-model, 517-languages, afrocentric, ubc-nlp
Summary
InkubaLM-0.4B is a 400M-parameter open-weights small language model built from scratch by Lelapa AI for five low-resource African languages (isiZulu, Yoruba, Swahili, isiXhosa, Hausa, plus English/French), using a LLaMA-style architecture trained on 2.4B tokens.
A massively multilingual masked language model covering 517 African languages and varieties across five scripts, achieving state-of-the-art results on the AfroNLU benchmark. Developed by the UBC Deep Learning and NLP Lab as an Afrocentric resource.