llama-tiny-fp8-quant-method
llama-tiny-fp8-quant-method is a chat model from amd-quark, released February 7, 2025. llama-tiny-fp8-quant-method is an open-weights chat model.
by amd-quark
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use llama-tiny-fp8-quant-method in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your amd-quark API key. osFoundry discovers llama-tiny-fp8-quant-method 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
llama-tiny-fp8-quant-method 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.
llama-tiny-fp8-quant-method vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about llama-tiny-fp8-quant-method
Is llama-tiny-fp8-quant-method free to use?
llama-tiny-fp8-quant-method 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 llama-tiny-fp8-quant-method commercially?
Commercial use is allowed with conditions. Licence terms not specified — verify the upstream model card before commercial use. Check upstream documentation.
Can I run llama-tiny-fp8-quant-method locally?
Yes. llama-tiny-fp8-quant-method is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is llama-tiny-fp8-quant-method best at?
llama-tiny-fp8-quant-method is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use llama-tiny-fp8-quant-method in osFoundry?
Paste your amd-quark API key in the key dialog (or deploy the open weights for self-hostable models), assign llama-tiny-fp8-quant-method to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by amd-quark on February 7, 2025. Source: https://huggingface.co/amd-quark/llama-tiny-fp8-quant-method