granite-3.3-8b-instruct-gptqmodel-4b-64g
Built by jeffcookio, granite-3.3-8b-instruct-gptqmodel-4b-64g is a 8 billion parameter chat model. granite-3.3-8b-instruct-gptqmodel-4b-64g is an open-weights chat model with roughly 8 billion parameters.
by jeffcookio · 8B parameters
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use granite-3.3-8b-instruct-gptqmodel-4b-64g in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your jeffcookio API key. osFoundry discovers granite-3.3-8b-instruct-gptqmodel-4b-64g 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
granite-3.3-8b-instruct-gptqmodel-4b-64g 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 granite-3.3-8b-instruct-gptqmodel-4b-64g
granite-3.3-8b-instruct-gptqmodel-4b-64g 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).
granite-3.3-8b-instruct-gptqmodel-4b-64g vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about granite-3.3-8b-instruct-gptqmodel-4b-64g
Is granite-3.3-8b-instruct-gptqmodel-4b-64g free to use?
granite-3.3-8b-instruct-gptqmodel-4b-64g 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 granite-3.3-8b-instruct-gptqmodel-4b-64g 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 granite-3.3-8b-instruct-gptqmodel-4b-64g need?
Approximately 5 GB at Q4 quantisation, or 20 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run granite-3.3-8b-instruct-gptqmodel-4b-64g locally?
Yes. granite-3.3-8b-instruct-gptqmodel-4b-64g is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is granite-3.3-8b-instruct-gptqmodel-4b-64g best at?
granite-3.3-8b-instruct-gptqmodel-4b-64g is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use granite-3.3-8b-instruct-gptqmodel-4b-64g in osFoundry?
Paste your jeffcookio API key in the key dialog (or deploy the open weights for self-hostable models), assign granite-3.3-8b-instruct-gptqmodel-4b-64g to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by jeffcookio on April 16, 2025. Source: https://huggingface.co/jeffcookio/granite-3.3-8b-instruct-gptqmodel-4b-64g