<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/flux-2-small-decoder-and-gemma-4-12b-it-models-now-available-on-amazon-sagemaker-jumpstart-nxy90napn" -->

---
title: FLUX.2-small-decoder and gemma-4-12B-it models now...
description: Black Forest Labs' FLUX.2-small-decoder and Google's gemma-4-12B-it are now available on Amazon SageMaker JumpStart. FLUX.2-small-decoder is a distilled VAE...
canonical: https://daily.dev/posts/flux-2-small-decoder-and-gemma-4-12b-it-models-now-available-on-amazon-sagemaker-jumpstart-nxy90napn
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: FLUX.2-small-decoder and gemma-4-12B-it models now available on Amazon SageMaker JumpStart | daily.dev
og:description: Black Forest Labs' FLUX.2-small-decoder and Google's gemma-4-12B-it are now available on Amazon SageMaker JumpStart. FLUX.2-small-decoder is a distilled VAE...
og:url: https://daily.dev/posts/flux-2-small-decoder-and-gemma-4-12b-it-models-now-available-on-amazon-sagemaker-jumpstart-nxy90napn
og:image: https://api.daily.dev/og/posts/nXy90napN.png
og:image:alt: FLUX.2-small-decoder and gemma-4-12B-it models now available on Amazon SageMaker JumpStart
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# FLUX.2-small-decoder and gemma-4-12B-it models now available on Amazon SageMaker JumpStart

**[AWS](https://daily.dev/sources/aws)** · 2 min read · 1 upvotes · 0 comments

## Summary

Black Forest Labs' FLUX.2-small-decoder and Google's gemma-4-12B-it are now available on Amazon SageMaker JumpStart. FLUX.2-small-decoder is a distilled VAE decoder offering ~1.4× faster image decoding at 1.4× lower VRAM usage compared to the standard FLUX.2 decoder, with minimal quality loss — benefits scale at higher resolutions. gemma-4-12B-it is a 12B multimodal model supporting text, image, and audio inputs with native function calling and agentic workflows. Its encoder-free, decoder-only transformer architecture delivers performance close to Google's 26B MoE model while running on just 16GB of RAM. Both models can be deployed via the SageMaker console or Python SDK.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://aws.amazon.com/about-aws/whats-new/2026/01/flux.2-small-decoder-gemma-4-12B-it-on-sagemaker-jumpstart>

## Questions this post answers

### What is FLUX.2-small-decoder and how much faster is it than the standard FLUX.2 decoder?

FLUX.2-small-decoder is a distilled VAE decoder that acts as a drop-in replacement for the standard FLUX.2 image generation decoder. It delivers approximately 1.4x faster decoding speed and 1.4x lower VRAM consumption with minimal to zero quality loss, and the benefits grow further at higher image resolutions since more pixels are processed. It is now available through Amazon SageMaker JumpStart.

_Teams optimizing image generation pipelines can track model updates like this one on daily.dev._

### How much memory does Google's gemma-4-12B-it model require to run and how does it compare to the 26B MoE model?

Gemma-4-12B-it can run on as little as 16GB of RAM. It uses an encoder-free architecture where text, image, and audio inputs flow directly into a single decoder-only transformer, delivering performance nearing Google's larger 26B MoE model at less than half the memory footprint, making it suitable for enterprise multimodal and agentic deployments.

_daily.dev helps engineers evaluating multimodal model tradeoffs stay on top of new releases._

## Similar posts on daily.dev

- [Gemma 4 12B Enables On-Device, Multimodal Agentic Workflows with an Encoder-free Architecture](https://daily.dev/posts/gemma-4-12b-enables-on-device-multimodal-agentic-workflows-with-an-encoder-free-architecture-wieojqluc) · InfoQ · 1 upvotes · 0 comments
- [T5Gemma 2: The next generation of encoder-decoder models](https://daily.dev/posts/t5gemma-2-the-next-generation-of-encoder-decoder-models-nyxpiksgp) · Hacker News · 1 upvotes · 0 comments
- [Gemma-4-31B-it-assistant and Gemma-4-31B-IT-NVFP4 models now available on Amazon SageMaker JumpStart](https://daily.dev/posts/gemma-4-31b-it-assistant-and-gemma-4-31b-it-nvfp4-models-now-available-on-amazon-sagemaker-jumpstart-fljueia5d) · AWS · 0 upvotes · 0 comments
- [I tested Google's new Gemma 4 12B on my 8GB GPU, and now I don't want to go back to smaller models](https://daily.dev/posts/i-tested-google-s-new-gemma-4-12b-on-my-8gb-gpu-and-now-i-don-t-want-to-go-back-to-smaller-models-7rdzvdak0) · XDA Developers · 0 upvotes · 0 comments

---

Tags: [#ai](https://daily.dev/tags/ai), [#machine-learning](https://daily.dev/tags/machine-learning), [#aws](https://daily.dev/tags/aws), [#genai](https://daily.dev/tags/genai), [#multimodal](https://daily.dev/tags/multimodal)

[View this post on daily.dev](https://daily.dev/posts/flux-2-small-decoder-and-gemma-4-12b-it-models-now-available-on-amazon-sagemaker-jumpstart-nxy90napn)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"FLUX.2-small-decoder and gemma-4-12B-it models now available on Amazon SageMaker JumpStart","url":"https://daily.dev/posts/flux-2-small-decoder-and-gemma-4-12b-it-models-now-available-on-amazon-sagemaker-jumpstart-nxy90napn","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/flux-2-small-decoder-and-gemma-4-12b-it-models-now-available-on-amazon-sagemaker-jumpstart-nxy90napn"},"datePublished":"2026-08-11T01:06:22.423Z","dateModified":"2026-09-14T09:00:57.694Z","description":"Black Forest Labs' FLUX.2-small-decoder and Google's gemma-4-12B-it are now available on Amazon SageMaker JumpStart. FLUX.2-small-decoder is a distilled VAE...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/2d99c2aecc14a73a5cba88addc902c88?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/2d99c2aecc14a73a5cba88addc902c88?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"AWS","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"AWS","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/aws","url":"https://daily.dev/sources/aws"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/flux-2-small-decoder-and-gemma-4-12b-it-models-now-available-on-amazon-sagemaker-jumpstart-nxy90napn","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai,machine-learning,aws,genai,multimodal","timeRequired":"PT2M"}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"AWS","item":"https://daily.dev/sources/aws"},{"@type":"ListItem","position":3,"name":"FLUX.2-small-decoder and gemma-4-12B-it models now available on Amazon SageMaker JumpStart"}]}
{"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/flux-2-small-decoder-and-gemma-4-12b-it-models-now-available-on-amazon-sagemaker-jumpstart-nxy90napn#faq","mainEntity":[{"@type":"Question","name":"What is FLUX.2-small-decoder and how much faster is it than the standard FLUX.2 decoder?","acceptedAnswer":{"@type":"Answer","text":"FLUX.2-small-decoder is a distilled VAE decoder that acts as a drop-in replacement for the standard FLUX.2 image generation decoder. It delivers approximately 1.4x faster decoding speed and 1.4x lower VRAM consumption with minimal to zero quality loss, and the benefits grow further at higher image resolutions since more pixels are processed. It is now available through Amazon SageMaker JumpStart. Teams optimizing image generation pipelines can track model updates like this one on daily.dev."}},{"@type":"Question","name":"How much memory does Google's gemma-4-12B-it model require to run and how does it compare to the 26B MoE model?","acceptedAnswer":{"@type":"Answer","text":"Gemma-4-12B-it can run on as little as 16GB of RAM. It uses an encoder-free architecture where text, image, and audio inputs flow directly into a single decoder-only transformer, delivering performance nearing Google's larger 26B MoE model at less than half the memory footprint, making it suitable for enterprise multimodal and agentic deployments. daily.dev helps engineers evaluating multimodal model tradeoffs stay on top of new releases."}}]}
```