provn-gemma4-e2b-q4km
provn-gemma4-e2b-q4km is a 2 billion parameter chat model from haifeng1976, released April 15, 2026. provn-gemma4-e2b-q4km is an open-weights chat model with roughly 2 billion parameters.
by haifeng1976 · 2B parameters
Best for
Ways to use provn-gemma4-e2b-q4km in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your haifeng1976 API key. osFoundry discovers provn-gemma4-e2b-q4km 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
provn-gemma4-e2b-q4km 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 provn-gemma4-e2b-q4km
provn-gemma4-e2b-q4km 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).
provn-gemma4-e2b-q4km vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about provn-gemma4-e2b-q4km
Is provn-gemma4-e2b-q4km free to use?
provn-gemma4-e2b-q4km 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 provn-gemma4-e2b-q4km 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 provn-gemma4-e2b-q4km need?
Approximately 2 GB at Q4 quantisation, or 5 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run provn-gemma4-e2b-q4km locally?
Yes. provn-gemma4-e2b-q4km is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is provn-gemma4-e2b-q4km best at?
provn-gemma4-e2b-q4km is well-suited to text classification.
How do I use provn-gemma4-e2b-q4km in osFoundry?
Paste your haifeng1976 API key in the key dialog (or deploy the open weights for self-hostable models), assign provn-gemma4-e2b-q4km to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by haifeng1976 on April 15, 2026. Source: https://huggingface.co/haifeng1976/provn-gemma4-e2b-q4km