African team trains small model from scratch, self-reports benchmark lead
Vambo AI released MORENA; results are developer-reported. The interesting part is the custom tokenizer cutting African text encoding cost; independent replication pending.
Original event 2026-09-18
Vambo AI has released MORENA, a 1.5B-parameter model trained from scratch for 12 African languages, with self-reported benchmark results ahead of 26 tested models.
The developers report 1.408 bpb on African language modelling, the best of 26 models tested; the closest rival, Lugha-Llama-8B, carries over five times the parameters and scored 1.423 bpb. All figures are developer-reported, relayed via TechRadar, with no independent replication yet.
The mechanism difference is a custom vocabulary: African text encodes with 1.39 times fewer tokens than Gemma 3, though it still costs about 6% more tokens per byte than English, a gap the team says it cannot fully explain. Training took roughly 22,000 A100 GPU hours, with compute support from UNDP and others.