Lugha-Llama-8B-wura_edu
Lugha-Llama-8B-wura_edu (Lugha-Llama, 2024) is a 8 billion parameter chat model. Lugha-Llama-8B-wura_edu is an open-weights chat model with roughly 8 billion parameters.
by Lugha-Llama · 8B parameters
Best for
Ways to use Lugha-Llama-8B-wura_edu in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Lugha-Llama API key. osFoundry discovers Lugha-Llama-8B-wura_edu automatically — assign it to a Maestro role (router, direct, orchestrator, or fallback) in the Pipeline tab and it is live in every chat. Your key, your provider account — no token markup.
Deploy a dedicated endpoint
Lugha-Llama-8B-wura_edu is open-weights — run it locally for free, or deploy a dedicated GPU endpoint in your workspace for reserved capacity with no rate limits.
Use it in a Room App
Room Apps declare AI features in their manifest, then call them with invokeAI:
import { invokeAI } from '@osfoundry/app-sdk'
// 'summarize' is an AI feature declared in your app manifest.
const result = await invokeAI('summarize', userText)
Call it from your own apps
Once a model is wired into your workspace you can host it as an API and reach it from your own services, scripts, or CI — outside osFoundry.
What hardware can run Lugha-Llama-8B-wura_edu
Lugha-Llama-8B-wura_edu runs on a single 16GB consumer GPU (~5 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~20 GB).
Lugha-Llama-8B-wura_edu vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Lugha-Llama-8B-wura_edu
Is Lugha-Llama-8B-wura_edu free to use?
Lugha-Llama-8B-wura_edu is free to run locally on your own hardware. Hosted access through osFoundry is metered (input Free (local), output Free (local)). You can switch between local and hosted at any time.
Can I use Lugha-Llama-8B-wura_edu commercially?
Commercial use is allowed with conditions. Licence terms not specified — verify the upstream model card before commercial use. Check upstream documentation.
How much VRAM does Lugha-Llama-8B-wura_edu need?
Approximately 5 GB at Q4 quantisation, or 20 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Lugha-Llama-8B-wura_edu locally?
Yes. Lugha-Llama-8B-wura_edu is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Lugha-Llama-8B-wura_edu best at?
Lugha-Llama-8B-wura_edu is well-suited to text generation.
How do I use Lugha-Llama-8B-wura_edu in osFoundry?
Paste your Lugha-Llama API key in the key dialog (or deploy the open weights for self-hostable models), assign Lugha-Llama-8B-wura_edu to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Lugha-Llama on December 13, 2024. Source: https://huggingface.co/Lugha-Llama/Lugha-Llama-8B-wura_edu