Lumina-mGPT-7B-512
Built by Alpha-VLLM, Lumina-mGPT-7B-512 is a 7 billion parameter chat model. Lumina-mGPT-7B-512 is an open-weights chat model with roughly 7 billion parameters.
by Alpha-VLLM · 7B parameters
Best for
Ways to use Lumina-mGPT-7B-512 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Alpha-VLLM API key. osFoundry discovers Lumina-mGPT-7B-512 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
Lumina-mGPT-7B-512 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 Lumina-mGPT-7B-512
Lumina-mGPT-7B-512 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 (~17 GB).
Lumina-mGPT-7B-512 vs similar models
| Model | Org | Params | Context | Input price | Self-host |
|---|
| Lumina-mGPT-7B-512 | Alpha-VLLM | 7B | — | Free (local) | Yes |
| Claire-7B-0.1 | OpenLLM-France | 7B | — | Free (local) | Yes |
| xLAM-8x7b-r | Salesforce | 7B | — | Free (local) | Yes |
| BlueLM-7B-Chat | vivo-ai | 7B | — | Free (local) | Yes |
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Lumina-mGPT-7B-512
Is Lumina-mGPT-7B-512 free to use?
Lumina-mGPT-7B-512 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 Lumina-mGPT-7B-512 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 Lumina-mGPT-7B-512 need?
Approximately 5 GB at Q4 quantisation, or 17 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Lumina-mGPT-7B-512 locally?
Yes. Lumina-mGPT-7B-512 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Lumina-mGPT-7B-512 best at?
Lumina-mGPT-7B-512 is well-suited to any to any.
How do I use Lumina-mGPT-7B-512 in osFoundry?
Paste your Alpha-VLLM API key in the key dialog (or deploy the open weights for self-hostable models), assign Lumina-mGPT-7B-512 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Alpha-VLLM on August 4, 2024. Source: https://huggingface.co/Alpha-VLLM/Lumina-mGPT-7B-512