Llama-3.1-70B
Built by unsloth, Llama-3.1-70B is a 70 billion parameter chat model. Llama-3.1-70B is an open-weights chat model with roughly 70 billion parameters.
by unsloth · 70B parameters
Best for
Ways to use Llama-3.1-70B in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your unsloth API key. osFoundry discovers Llama-3.1-70B 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-3.1-70B 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-3.1-70B
Llama-3.1-70B runs on a single A100 80GB or H100 80GB at Q4 quantisation (~42 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~168 GB).
Llama-3.1-70B vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Llama-3.1-70B
Is Llama-3.1-70B free to use?
Llama-3.1-70B 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-3.1-70B 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-3.1-70B need?
Approximately 42 GB at Q4 quantisation, or 168 GB at full FP16 precision. Fits on a single A100/H100 80GB.
Can I run Llama-3.1-70B locally?
Yes. Llama-3.1-70B is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Llama-3.1-70B best at?
Llama-3.1-70B is well-suited to text generation.
How do I use Llama-3.1-70B in osFoundry?
Paste your unsloth API key in the key dialog (or deploy the open weights for self-hostable models), assign Llama-3.1-70B to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by unsloth on November 20, 2025. Source: https://huggingface.co/unsloth/Llama-3.1-70B