gemma-4-19B-A4B-it-INSTRUCT-Heretic-Uncensored-mlx_JANG_4M
gemma-4-19B-A4B-it-INSTRUCT-Heretic-Uncensored-mlx_JANG_4M is a 19 billion parameter image-generation model from WaveCut, released April 20, 2026. gemma-4-19B-A4B-it-INSTRUCT-Heretic-Uncensored-mlx_JANG_4M is an open-weights image model with roughly 19 billion parameters.
by WaveCut · 19B parameters
Best for
Ways to use gemma-4-19B-A4B-it-INSTRUCT-Heretic-Uncensored-mlx_JANG_4M in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your WaveCut API key. osFoundry discovers gemma-4-19B-A4B-it-INSTRUCT-Heretic-Uncensored-mlx_JANG_4M 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-4-19B-A4B-it-INSTRUCT-Heretic-Uncensored-mlx_JANG_4M 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-4-19B-A4B-it-INSTRUCT-Heretic-Uncensored-mlx_JANG_4M
gemma-4-19B-A4B-it-INSTRUCT-Heretic-Uncensored-mlx_JANG_4M runs on a single 16GB consumer GPU (~12 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~46 GB).
gemma-4-19B-A4B-it-INSTRUCT-Heretic-Uncensored-mlx_JANG_4M vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about gemma-4-19B-A4B-it-INSTRUCT-Heretic-Uncensored-mlx_JANG_4M
Is gemma-4-19B-A4B-it-INSTRUCT-Heretic-Uncensored-mlx_JANG_4M free to use?
gemma-4-19B-A4B-it-INSTRUCT-Heretic-Uncensored-mlx_JANG_4M 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-4-19B-A4B-it-INSTRUCT-Heretic-Uncensored-mlx_JANG_4M 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-4-19B-A4B-it-INSTRUCT-Heretic-Uncensored-mlx_JANG_4M need?
Approximately 12 GB at Q4 quantisation, or 46 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run gemma-4-19B-A4B-it-INSTRUCT-Heretic-Uncensored-mlx_JANG_4M locally?
Yes. gemma-4-19B-A4B-it-INSTRUCT-Heretic-Uncensored-mlx_JANG_4M is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is gemma-4-19B-A4B-it-INSTRUCT-Heretic-Uncensored-mlx_JANG_4M best at?
gemma-4-19B-A4B-it-INSTRUCT-Heretic-Uncensored-mlx_JANG_4M is well-suited to image text to text.
How do I use gemma-4-19B-A4B-it-INSTRUCT-Heretic-Uncensored-mlx_JANG_4M in osFoundry?
Paste your WaveCut API key in the key dialog (or deploy the open weights for self-hostable models), assign gemma-4-19B-A4B-it-INSTRUCT-Heretic-Uncensored-mlx_JANG_4M to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by WaveCut on April 20, 2026. Source: https://huggingface.co/WaveCut/gemma-4-19B-A4B-it-INSTRUCT-Heretic-Uncensored-mlx_JANG_4M