Fimbulvetr-11B-v2.1-16K
Released by Sao10K in 2024, Fimbulvetr-11B-v2.1-16K is a 11 billion parameter chat model. Fimbulvetr-11B-v2.1-16K is an open-weights chat model with roughly 11 billion parameters.
by Sao10K · 11B parameters
Best for
Ways to use Fimbulvetr-11B-v2.1-16K in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Sao10K API key. osFoundry discovers Fimbulvetr-11B-v2.1-16K 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
Fimbulvetr-11B-v2.1-16K 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 Fimbulvetr-11B-v2.1-16K
Fimbulvetr-11B-v2.1-16K runs on a single 16GB consumer GPU (~7 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~27 GB).
Fimbulvetr-11B-v2.1-16K vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Fimbulvetr-11B-v2.1-16K
Is Fimbulvetr-11B-v2.1-16K free to use?
Fimbulvetr-11B-v2.1-16K 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 Fimbulvetr-11B-v2.1-16K 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 Fimbulvetr-11B-v2.1-16K need?
Approximately 7 GB at Q4 quantisation, or 27 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Fimbulvetr-11B-v2.1-16K locally?
Yes. Fimbulvetr-11B-v2.1-16K is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Fimbulvetr-11B-v2.1-16K best at?
Fimbulvetr-11B-v2.1-16K is well-suited to text generation.
How do I use Fimbulvetr-11B-v2.1-16K in osFoundry?
Paste your Sao10K API key in the key dialog (or deploy the open weights for self-hostable models), assign Fimbulvetr-11B-v2.1-16K to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Sao10K on June 25, 2024. Source: https://huggingface.co/Sao10K/Fimbulvetr-11B-v2.1-16K