omost-llama-3-8b-4bits
Released by lllyasviel in 2024, omost-llama-3-8b-4bits is a 8 billion parameter chat model. omost-llama-3-8b-4bits is an open-weights chat model with roughly 8 billion parameters.
by lllyasviel · 8B parameters
Best for
Ways to use omost-llama-3-8b-4bits in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your lllyasviel API key. osFoundry discovers omost-llama-3-8b-4bits 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
omost-llama-3-8b-4bits 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 omost-llama-3-8b-4bits
omost-llama-3-8b-4bits 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).
omost-llama-3-8b-4bits vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about omost-llama-3-8b-4bits
Is omost-llama-3-8b-4bits free to use?
omost-llama-3-8b-4bits 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 omost-llama-3-8b-4bits 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 omost-llama-3-8b-4bits need?
Approximately 5 GB at Q4 quantisation, or 20 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run omost-llama-3-8b-4bits locally?
Yes. omost-llama-3-8b-4bits is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is omost-llama-3-8b-4bits best at?
omost-llama-3-8b-4bits is well-suited to text generation.
How do I use omost-llama-3-8b-4bits in osFoundry?
Paste your lllyasviel API key in the key dialog (or deploy the open weights for self-hostable models), assign omost-llama-3-8b-4bits to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by lllyasviel on May 29, 2024. Source: https://huggingface.co/lllyasviel/omost-llama-3-8b-4bits