gemma-4-26b-a4b-it-mxfp4-moe-juju
storagejuju's gemma-4-26b-a4b-it-mxfp4-moe-juju packs 26 billion parameters into a chat model. gemma-4-26b-a4b-it-mxfp4-moe-juju is an open-weights chat model with roughly 26 billion parameters.
by storagejuju · 26B parameters
Best for
Ways to use gemma-4-26b-a4b-it-mxfp4-moe-juju in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your storagejuju API key. osFoundry discovers gemma-4-26b-a4b-it-mxfp4-moe-juju 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-4-26b-a4b-it-mxfp4-moe-juju 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-4-26b-a4b-it-mxfp4-moe-juju
gemma-4-26b-a4b-it-mxfp4-moe-juju runs on a single 16GB consumer GPU (~16 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~63 GB).
gemma-4-26b-a4b-it-mxfp4-moe-juju vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about gemma-4-26b-a4b-it-mxfp4-moe-juju
Is gemma-4-26b-a4b-it-mxfp4-moe-juju free to use?
gemma-4-26b-a4b-it-mxfp4-moe-juju 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-4-26b-a4b-it-mxfp4-moe-juju 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-4-26b-a4b-it-mxfp4-moe-juju need?
Approximately 16 GB at Q4 quantisation, or 63 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run gemma-4-26b-a4b-it-mxfp4-moe-juju locally?
Yes. gemma-4-26b-a4b-it-mxfp4-moe-juju is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is gemma-4-26b-a4b-it-mxfp4-moe-juju best at?
gemma-4-26b-a4b-it-mxfp4-moe-juju is well-suited to text generation.
How do I use gemma-4-26b-a4b-it-mxfp4-moe-juju in osFoundry?
Paste your storagejuju API key in the key dialog (or deploy the open weights for self-hostable models), assign gemma-4-26b-a4b-it-mxfp4-moe-juju to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by storagejuju on May 10, 2026. Source: https://huggingface.co/storagejuju/gemma-4-26b-a4b-it-mxfp4-moe-juju