gemma-4-E4B-it-JANG_4L
gemma-4-E4B-it-JANG_4L (bearzi, 2026) is a 4 billion parameter chat model. gemma-4-E4B-it-JANG_4L is an open-weights chat model with roughly 4 billion parameters.
by bearzi · 4B parameters
Best for
Ways to use gemma-4-E4B-it-JANG_4L in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your bearzi API key. osFoundry discovers gemma-4-E4B-it-JANG_4L 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-4-E4B-it-JANG_4L 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-4-E4B-it-JANG_4L
gemma-4-E4B-it-JANG_4L runs on a single 16GB consumer GPU (~3 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~10 GB).
gemma-4-E4B-it-JANG_4L vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about gemma-4-E4B-it-JANG_4L
Is gemma-4-E4B-it-JANG_4L free to use?
gemma-4-E4B-it-JANG_4L 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-4-E4B-it-JANG_4L 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-4-E4B-it-JANG_4L need?
Approximately 3 GB at Q4 quantisation, or 10 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run gemma-4-E4B-it-JANG_4L locally?
Yes. gemma-4-E4B-it-JANG_4L is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is gemma-4-E4B-it-JANG_4L best at?
gemma-4-E4B-it-JANG_4L is well-suited to text generation.
How do I use gemma-4-E4B-it-JANG_4L in osFoundry?
Paste your bearzi API key in the key dialog (or deploy the open weights for self-hostable models), assign gemma-4-E4B-it-JANG_4L to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by bearzi on April 27, 2026. Source: https://huggingface.co/bearzi/gemma-4-E4B-it-JANG_4L