Anubis-Pro-105B-NVFP4
Released by Kaleto in 2026, Anubis-Pro-105B-NVFP4 is a 105 billion parameter chat model. Anubis-Pro-105B-NVFP4 is an open-weights chat model with roughly 105 billion parameters.
by Kaleto · 105B parameters
Best for
Ways to use Anubis-Pro-105B-NVFP4 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Kaleto API key. osFoundry discovers Anubis-Pro-105B-NVFP4 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
Anubis-Pro-105B-NVFP4 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 Anubis-Pro-105B-NVFP4
Anubis-Pro-105B-NVFP4 runs on a single A100 80GB or H100 80GB at Q4 quantisation (~63 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~252 GB).
Anubis-Pro-105B-NVFP4 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Anubis-Pro-105B-NVFP4
Is Anubis-Pro-105B-NVFP4 free to use?
Anubis-Pro-105B-NVFP4 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 Anubis-Pro-105B-NVFP4 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 Anubis-Pro-105B-NVFP4 need?
Approximately 63 GB at Q4 quantisation, or 252 GB at full FP16 precision. Fits on a single A100/H100 80GB.
Can I run Anubis-Pro-105B-NVFP4 locally?
Yes. Anubis-Pro-105B-NVFP4 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Anubis-Pro-105B-NVFP4 best at?
Anubis-Pro-105B-NVFP4 is well-suited to text generation.
How do I use Anubis-Pro-105B-NVFP4 in osFoundry?
Paste your Kaleto API key in the key dialog (or deploy the open weights for self-hostable models), assign Anubis-Pro-105B-NVFP4 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Kaleto on May 13, 2026. Source: https://huggingface.co/Kaleto/Anubis-Pro-105B-NVFP4