Llama-3.3-70B-Instruct-speculator.eagle3
Llama-3.3-70B-Instruct-speculator.eagle3 (RedHatAI, 2025) is a 70 billion parameter chat model. Llama-3.3-70B-Instruct-speculator.eagle3 is an open-weights chat model with roughly 70 billion parameters.
by RedHatAI · 70B parameters
Best for
Ways to use Llama-3.3-70B-Instruct-speculator.eagle3 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your RedHatAI API key. osFoundry discovers Llama-3.3-70B-Instruct-speculator.eagle3 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-3.3-70B-Instruct-speculator.eagle3 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-3.3-70B-Instruct-speculator.eagle3
Llama-3.3-70B-Instruct-speculator.eagle3 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-3.3-70B-Instruct-speculator.eagle3 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Llama-3.3-70B-Instruct-speculator.eagle3
Is Llama-3.3-70B-Instruct-speculator.eagle3 free to use?
Llama-3.3-70B-Instruct-speculator.eagle3 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-3.3-70B-Instruct-speculator.eagle3 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-3.3-70B-Instruct-speculator.eagle3 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-3.3-70B-Instruct-speculator.eagle3 locally?
Yes. Llama-3.3-70B-Instruct-speculator.eagle3 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Llama-3.3-70B-Instruct-speculator.eagle3 best at?
Llama-3.3-70B-Instruct-speculator.eagle3 is well-suited to text generation.
How do I use Llama-3.3-70B-Instruct-speculator.eagle3 in osFoundry?
Paste your RedHatAI API key in the key dialog (or deploy the open weights for self-hostable models), assign Llama-3.3-70B-Instruct-speculator.eagle3 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by RedHatAI on September 18, 2025. Source: https://huggingface.co/RedHatAI/Llama-3.3-70B-Instruct-speculator.eagle3