Skip to content
AI Resources

InkubaLM vs Lugha-Llama

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.

Category
AI Resources
AI Resources
Type
LLM
LLM
Country
🇿🇦 South Africa
🌍 Pan-African
Docs status
Docs live
Docs live
Licensing
Pricing
Free / open weights (CC BY-NC 4.0)
Open weights (Llama 3.1 community license)
Verified
Verified
Unverified
Last verified
10 Oct 2026
10 Oct 2026
Tags
nlp, llm, african-languages, open-weights, low-resource
african-languages, swahili, low-resource, wura-corpus, llama-3.1
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.
Lugha-Llama is a Llama-3.1-8B model continually pretrained on the WURA African-language corpus to lift performance on low-resource African languages. It ships in three variants (wura, wura_edu, wura_math) and reaches leading results among similarly sized models on the IrokoBench and AfriQA African-language benchmarks. It was built by researchers at Princeton University.

InkubaLM vs Lugha-Llama at a glance

InkubaLM and Lugha-Llama are both listed under LLM in Wycord's AI Resources index.

InkubaLM is based in South Africa and Lugha-Llama in Pan-African.

Both currently show the status "Docs live".

On access, both are marked "No approval needed".

Over the last 30 days Wycord's probes measured 100% uptime for InkubaLM (36 checks) and 100% for Lugha-Llama (36 checks).

Average response time on live probes was 168 ms for InkubaLM and 152 ms for Lugha-Llama.

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

How they differ

  • Pricing: InkubaLM, Free / open weights (CC BY-NC 4.0); Lugha-Llama, Open weights (Llama 3.1 community license).
  • Country: InkubaLM, South Africa; Lugha-Llama, Pan-African.
  • Verification: InkubaLM, Verified; Lugha-Llama, Unverified.
  • Average latency: InkubaLM, 168 ms; Lugha-Llama, 152 ms.

Topics

Both are tagged: african-languages, low-resource.

Only InkubaLM: nlp, llm, open-weights.

Only Lugha-Llama: swahili, wura-corpus, llama-3.1.

Common questions

Which has better uptime, InkubaLM or Lugha-Llama?
They are level at 100% over the last 30 days.
Do InkubaLM or Lugha-Llama need approval before use?
Both are marked "No approval needed".
Is the documentation for InkubaLM and Lugha-Llama working?
Both show "Docs live" at the last check.
Where are InkubaLM and Lugha-Llama based?
InkubaLM is based in South Africa; Lugha-Llama is based in Pan-African.

More comparisons