llama-33B-instructed
llama-33B-instructed (Secbone, 2023) is a 33 billion parameter chat model. llama-33B-instructed is an open-weights chat model with roughly 33 billion parameters.
by Secbone · 33B parameters
Best for
Ways to use llama-33B-instructed in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Secbone API key. osFoundry discovers llama-33B-instructed 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
llama-33B-instructed 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 llama-33B-instructed
llama-33B-instructed runs on a 24GB consumer or workstation GPU (~20 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~80 GB).
llama-33B-instructed vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about llama-33B-instructed
Is llama-33B-instructed free to use?
llama-33B-instructed 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 llama-33B-instructed 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 llama-33B-instructed need?
Approximately 20 GB at Q4 quantisation, or 80 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run llama-33B-instructed locally?
Yes. llama-33B-instructed is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is llama-33B-instructed best at?
llama-33B-instructed is well-suited to text generation.
How do I use llama-33B-instructed in osFoundry?
Paste your Secbone API key in the key dialog (or deploy the open weights for self-hostable models), assign llama-33B-instructed to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Secbone on September 18, 2023. Source: https://huggingface.co/Secbone/llama-33B-instructed