gemma-2-2b-it-quantized.w8a8
gemma-2-2b-it-quantized.w8a8 is a 2 billion parameter chat model from RedHatAI, released August 16, 2024. gemma-2-2b-it-quantized.w8a8 is an open-weights chat model with roughly 2 billion parameters.
by RedHatAI · 2B parameters
Best for
Ways to use gemma-2-2b-it-quantized.w8a8 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your RedHatAI API key. osFoundry discovers gemma-2-2b-it-quantized.w8a8 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
gemma-2-2b-it-quantized.w8a8 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 gemma-2-2b-it-quantized.w8a8
gemma-2-2b-it-quantized.w8a8 runs on a single 16GB consumer GPU (~2 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~5 GB).
gemma-2-2b-it-quantized.w8a8 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about gemma-2-2b-it-quantized.w8a8
Is gemma-2-2b-it-quantized.w8a8 free to use?
gemma-2-2b-it-quantized.w8a8 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 gemma-2-2b-it-quantized.w8a8 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 gemma-2-2b-it-quantized.w8a8 need?
Approximately 2 GB at Q4 quantisation, or 5 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run gemma-2-2b-it-quantized.w8a8 locally?
Yes. gemma-2-2b-it-quantized.w8a8 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is gemma-2-2b-it-quantized.w8a8 best at?
gemma-2-2b-it-quantized.w8a8 is well-suited to text generation.
How do I use gemma-2-2b-it-quantized.w8a8 in osFoundry?
Paste your RedHatAI API key in the key dialog (or deploy the open weights for self-hostable models), assign gemma-2-2b-it-quantized.w8a8 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by RedHatAI on August 16, 2024. Source: https://huggingface.co/RedHatAI/gemma-2-2b-it-quantized.w8a8