1a_meta-llama-Llama-3.1-405B-Instruct-fsdp-lr1e-5
1a_meta-llama-Llama-3.1-405B-Instruct-fsdp-lr1e-5 is a 405 billion parameter chat model from jplhughes2, released February 14, 2025. 1a_meta-llama-Llama-3.1-405B-Instruct-fsdp-lr1e-5 is an open-weights chat model with roughly 405 billion parameters.
by jplhughes2 · 405B parameters
Best for
- complex multi-step reasoning
- agent orchestration with tool use
- long-document analysis and summarisation
Ways to use 1a_meta-llama-Llama-3.1-405B-Instruct-fsdp-lr1e-5 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your jplhughes2 API key. osFoundry discovers 1a_meta-llama-Llama-3.1-405B-Instruct-fsdp-lr1e-5 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
1a_meta-llama-Llama-3.1-405B-Instruct-fsdp-lr1e-5 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 1a_meta-llama-Llama-3.1-405B-Instruct-fsdp-lr1e-5
1a_meta-llama-Llama-3.1-405B-Instruct-fsdp-lr1e-5 runs on a multi-GPU setup or H200 141GB at Q4 (~243 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~972 GB).
1a_meta-llama-Llama-3.1-405B-Instruct-fsdp-lr1e-5 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about 1a_meta-llama-Llama-3.1-405B-Instruct-fsdp-lr1e-5
Is 1a_meta-llama-Llama-3.1-405B-Instruct-fsdp-lr1e-5 free to use?
1a_meta-llama-Llama-3.1-405B-Instruct-fsdp-lr1e-5 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 1a_meta-llama-Llama-3.1-405B-Instruct-fsdp-lr1e-5 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 1a_meta-llama-Llama-3.1-405B-Instruct-fsdp-lr1e-5 need?
Approximately 243 GB at Q4 quantisation, or 972 GB at full FP16 precision. Requires multi-GPU at higher quantisation.
Can I run 1a_meta-llama-Llama-3.1-405B-Instruct-fsdp-lr1e-5 locally?
Yes. 1a_meta-llama-Llama-3.1-405B-Instruct-fsdp-lr1e-5 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is 1a_meta-llama-Llama-3.1-405B-Instruct-fsdp-lr1e-5 best at?
1a_meta-llama-Llama-3.1-405B-Instruct-fsdp-lr1e-5 is well-suited to complex multi-step reasoning, agent orchestration with tool use, long-document analysis and summarisation.
How do I use 1a_meta-llama-Llama-3.1-405B-Instruct-fsdp-lr1e-5 in osFoundry?
Paste your jplhughes2 API key in the key dialog (or deploy the open weights for self-hostable models), assign 1a_meta-llama-Llama-3.1-405B-Instruct-fsdp-lr1e-5 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by jplhughes2 on February 14, 2025. Source: https://huggingface.co/jplhughes2/1a_meta-llama-Llama-3.1-405B-Instruct-fsdp-lr1e-5