Skip to content
Wycord
AI Resources

SabiYarn-125M vs SERENGETI

A verified, side-by-side comparison. Both records are status-checked by Wycord, so you are comparing what each actually offers today, not a stale listing.

SabiYarn-125MSERENGETI
Category
AI Resources
AI Resources
Type
LLM
LLM
Country
🇳🇬 Nigeria
🌍 Pan-African
Docs status
Docs live
Docs live
Licensing
Institutional only
Pricing
Open weights
Free for research; commercial use requires contacting authors
Verified
Unverified
Verified
Last verified
10 Oct 2026
10 Oct 2026
Tags
yoruba, hausa, igbo, nigerian-languages, gpt
nlp, masked-language-model, 517-languages, afrocentric, ubc-nlp
Links
Website Docs
Website Docs GitHub
Summary
SabiYarn-125M is a 125M-parameter decoder-only foundation model pretrained on Nigerian-language text, the first in the SabiYarn series. It supports English, Yoruba, Hausa, Igbo and Nigerian Pidgin plus Fulfulde, Efik and Urhobo, with fine-tuned variants for translation, NER, sentiment and diacritization. It was built by Aletheia.ai Research Lab and presented at the AfricaNLP 2025 workshop.
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.

SabiYarn-125M vs SERENGETI at a glance

SabiYarn-125M and SERENGETI are both listed under LLM in Wycord's AI Resources index.

SabiYarn-125M is based in Nigeria and SERENGETI in Pan-African.

Both currently show the status "Docs live".

On access, SabiYarn-125M is marked "No approval needed" and SERENGETI "Institutional only".

Over the last 30 days Wycord's probes measured 100% uptime for SabiYarn-125M (36 checks) and 100% for SERENGETI (36 checks).

Average response time on live probes was 151 ms for SabiYarn-125M and 162 ms for SERENGETI.

Uptime and latency come from Wycord's own probes of each resource's website, documentation and repository, run every six hours.

How they differ

  • Access: SabiYarn-125M, No approval needed; SERENGETI, Institutional only.
  • Pricing: SabiYarn-125M, Open weights; SERENGETI, Free for research; commercial use requires contacting authors.
  • Country: SabiYarn-125M, Nigeria; SERENGETI, Pan-African.
  • Verification: SabiYarn-125M, Unverified; SERENGETI, Verified.
  • Average latency: SabiYarn-125M, 151 ms; SERENGETI, 162 ms.

Topics

Only SabiYarn-125M: yoruba, hausa, igbo, nigerian-languages, gpt.

Only SERENGETI: nlp, masked-language-model, 517-languages, afrocentric, ubc-nlp.

Common questions

Which has better uptime, SabiYarn-125M or SERENGETI?
They are level at 100% over the last 30 days.
Do SabiYarn-125M or SERENGETI need approval before use?
SabiYarn-125M is marked "No approval needed" and SERENGETI "Institutional only".
Is the documentation for SabiYarn-125M and SERENGETI working?
Both show "Docs live" at the last check.
Where are SabiYarn-125M and SERENGETI based?
SabiYarn-125M is based in Nigeria; SERENGETI is based in Pan-African.

More comparisons

Full details: SabiYarn-125MFull details: SERENGETI