DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored is a 8 billion parameter chat model from aifeifei798, released July 27, 2024. DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored is an open-weights chat model with roughly 8 billion parameters.
by aifeifei798 · 8B parameters
Best for
Ways to use DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your aifeifei798 API key. osFoundry discovers DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored 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
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored 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 DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored runs on a single 16GB consumer GPU (~5 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~20 GB).
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
Is DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored free to use?
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored 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 DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored 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 DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored need?
Approximately 5 GB at Q4 quantisation, or 20 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored locally?
Yes. DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored best at?
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored is well-suited to text generation.
How do I use DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored in osFoundry?
Paste your aifeifei798 API key in the key dialog (or deploy the open weights for self-hostable models), assign DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by aifeifei798 on July 27, 2024. Source: https://huggingface.co/aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored