Hermes-4-405B
NousResearch's Hermes-4-405B packs 405 billion parameters into a chat model. Hermes-4-405B is an open-weights chat model with roughly 405 billion parameters.
by NousResearch · 405B parameters
Best for
Ways to use Hermes-4-405B in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your NousResearch API key. osFoundry discovers Hermes-4-405B 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
Hermes-4-405B 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.
Use Hermes-4-405B via API
Hermes-4-405B is also served by hosted API providers — use it via API (BYOK) if you would rather not manage GPUs. That page lists per-provider pricing.
What hardware can run Hermes-4-405B
Hermes-4-405B 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).
Hermes-4-405B vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Hermes-4-405B
Is Hermes-4-405B free to use?
Hermes-4-405B 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 Hermes-4-405B 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 Hermes-4-405B need?
Approximately 243 GB at Q4 quantisation, or 972 GB at full FP16 precision. Requires multi-GPU at higher quantisation.
Can I run Hermes-4-405B locally?
Yes. Hermes-4-405B is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Hermes-4-405B best at?
Hermes-4-405B is well-suited to text generation.
How do I use Hermes-4-405B in osFoundry?
Paste your NousResearch API key in the key dialog (or deploy the open weights for self-hostable models), assign Hermes-4-405B to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by NousResearch on August 6, 2025. Source: https://huggingface.co/NousResearch/Hermes-4-405B