Hermes-4-405B-exl3-2bpw
cpral's Hermes-4-405B-exl3-2bpw packs 405 billion parameters into a chat model. Hermes-4-405B-exl3-2bpw is an open-weights chat model with roughly 405 billion parameters.
by cpral · 405B parameters
Best for
Ways to use Hermes-4-405B-exl3-2bpw in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your cpral API key. osFoundry discovers Hermes-4-405B-exl3-2bpw 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-exl3-2bpw 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 Hermes-4-405B-exl3-2bpw
Hermes-4-405B-exl3-2bpw 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-exl3-2bpw 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-exl3-2bpw
Is Hermes-4-405B-exl3-2bpw free to use?
Hermes-4-405B-exl3-2bpw 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-exl3-2bpw 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-exl3-2bpw 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-exl3-2bpw locally?
Yes. Hermes-4-405B-exl3-2bpw 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-exl3-2bpw best at?
Hermes-4-405B-exl3-2bpw is well-suited to text generation.
How do I use Hermes-4-405B-exl3-2bpw in osFoundry?
Paste your cpral API key in the key dialog (or deploy the open weights for self-hostable models), assign Hermes-4-405B-exl3-2bpw to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by cpral on April 24, 2026. Source: https://huggingface.co/cpral/Hermes-4-405B-exl3-2bpw