#diffusiongemma — Public Fediverse posts

Once you've picked up a picture or uploaded your own, the #DiffusionGemma model running on #NVidia GPUs will tell you if the photo contains a cat, what kind of fur pattern it has, and how fluffy it is:

Once you've picked up a picture or uploaded your own, the #DiffusionGemma model running on #NVidia GPUs will tell you if the photo contains a cat, what kind of fur pattern it has, and how fluffy it is:

Once you've picked up a picture or uploaded your own, the #DiffusionGemma model running on #NVidia GPUs will tell you if the photo contains a cat, what kind of fur pattern it has, and how fluffy it is:

Once you've picked up a picture or uploaded your own, the #DiffusionGemma model running on #NVidia GPUs will tell you if the photo contains a cat, what kind of fur pattern it has, and how fluffy it is:

Is it a 😺 or not?

System 1 models like Typesafe AI's #jev model classify, evaluate truthiness, or give a score.

I built an app in #java with #micronautfw & #langchain4j hosted on #CloudRun to discover if a picture depicts a cat or not, thanks to #DiffusionGemma

https://purrfect-match.cloud.run/

Is it a 😺 or not?

System 1 models like Typesafe AI's #jev model classify, evaluate truthiness, or give a score.

I built an app in #java with #micronautfw & #langchain4j hosted on #CloudRun to discover if a picture depicts a cat or not, thanks to #DiffusionGemma

https://purrfect-match.cloud.run/

Is it a 😺 or not?

System 1 models like Typesafe AI's #jev model classify, evaluate truthiness, or give a score.

I built an app in #java with #micronautfw & #langchain4j hosted on #CloudRun to discover if a picture depicts a cat or not, thanks to #DiffusionGemma

https://purrfect-match.cloud.run/

Is it a 😺 or not?

System 1 models like Typesafe AI's #jev model classify, evaluate truthiness, or give a score.

I built an app in #java with #micronautfw & #langchain4j hosted on #CloudRun to discover if a picture depicts a cat or not, thanks to #DiffusionGemma

https://purrfect-match.cloud.run/

Instead of generating text token by token, "System 1" decision models (like #Jev) act as fast, deterministic decision engines. In a single forward pass, they output calibrated probabilities.

Here's how I turned #DiffusionGemma into a multimodal visual classifier in #Java! 🧵👇

Instead of generating text token by token, "System 1" decision models (like #Jev) act as fast, deterministic decision engines. In a single forward pass, they output calibrated probabilities.

Here's how I turned #DiffusionGemma into a multimodal visual classifier in #Java! 🧵👇

Instead of generating text token by token, "System 1" decision models (like #Jev) act as fast, deterministic decision engines. In a single forward pass, they output calibrated probabilities.

Here's how I turned #DiffusionGemma into a multimodal visual classifier in #Java! 🧵👇

Instead of generating text token by token, "System 1" decision models (like #Jev) act as fast, deterministic decision engines. In a single forward pass, they output calibrated probabilities.

Here's how I turned #DiffusionGemma into a multimodal visual classifier in #Java! 🧵👇

RT @vllm_project: DiffusionGemma-Jev läuft jetzt auf vLLM 🚀

mehr auf Arint.info

#AI #DeepLearning #DiffusionGemma #Inference #MachineLearning #vLLM #arint_info

https://x.com/vllm_project/status/2102670270129647953

RT @vllm_project: DiffusionGemma-Jev läuft jetzt auf vLLM 🚀

mehr auf Arint.info

#AI #DeepLearning #DiffusionGemma #Inference #MachineLearning #vLLM #arint_info

https://x.com/vllm_project/status/2102670270129647953

RT @vllm_project: DiffusionGemma-Jev läuft jetzt auf vLLM 🚀

mehr auf Arint.info

#AI #DeepLearning #DiffusionGemma #Inference #MachineLearning #vLLM #arint_info

https://x.com/vllm_project/status/2102670270129647953

RT @vllm_project: DiffusionGemma-Jev läuft jetzt auf vLLM 🚀

mehr auf Arint.info

#AI #DeepLearning #DiffusionGemma #Inference #MachineLearning #vLLM #arint_info

https://x.com/vllm_project/status/2102670270129647953

📜 Behold, the groundbreaking "DiffusionGemma #Technical Report"—a 2608-page opus of mind-numbing #jargon and self-congratulatory names that sounds like it was written by a committee named "Team #Overcomplication." 🤦‍♂️ It's a miracle anyone survived to submit this on July 31, 2026. 🌪️
https://arxiv.org/abs/2608.00146 #DiffusionGemma #Report #Team #mindnumbing #HackerNews #ngated

📜 Behold, the groundbreaking "DiffusionGemma #Technical Report"—a 2608-page opus of mind-numbing #jargon and self-congratulatory names that sounds like it was written by a committee named "Team #Overcomplication." 🤦‍♂️ It's a miracle anyone survived to submit this on July 31, 2026. 🌪️
https://arxiv.org/abs/2608.00146 #DiffusionGemma #Report #Team #mindnumbing #HackerNews #ngated

📜 Behold, the groundbreaking "DiffusionGemma #Technical Report"—a 2608-page opus of mind-numbing #jargon and self-congratulatory names that sounds like it was written by a committee named "Team #Overcomplication." 🤦‍♂️ It's a miracle anyone survived to submit this on July 31, 2026. 🌪️
https://arxiv.org/abs/2608.00146 #DiffusionGemma #Report #Team #mindnumbing #HackerNews #ngated

📜 Behold, the groundbreaking "DiffusionGemma #Technical Report"—a 2608-page opus of mind-numbing #jargon and self-congratulatory names that sounds like it was written by a committee named "Team #Overcomplication." 🤦‍♂️ It's a miracle anyone survived to submit this on July 31, 2026. 🌪️
https://arxiv.org/abs/2608.00146 #DiffusionGemma #Report #Team #mindnumbing #HackerNews #ngated

DiffusionGemma Technical Report

https://arxiv.org/abs/2608.00146

Comments: https://news.ycombinator.com/item?id=49374287

#HackerNews #DiffusionGemma #Technical #Report #research #innovation #technology #arxiv #AI

DiffusionGemma Technical Report

https://arxiv.org/abs/2608.00146

Comments: https://news.ycombinator.com/item?id=49374287

#HackerNews #DiffusionGemma #Technical #Report #research #innovation #technology #arxiv #AI

DiffusionGemma Technical Report

https://arxiv.org/abs/2608.00146

Comments: https://news.ycombinator.com/item?id=49374287

#HackerNews #DiffusionGemma #Technical #Report #research #innovation #technology #arxiv #AI

DiffusionGemma Technical Report

https://arxiv.org/abs/2608.00146

Comments: https://news.ycombinator.com/item?id=49374287

#HackerNews #DiffusionGemma #Technical #Report #research #innovation #technology #arxiv #AI

“Now that organisations have been weaned off earlier 'all you can eat' #subscription plans and onto 'pay-as-you-go' metered #token consumption, they're all in various stages of sticker shock.

Several talks at the conference discussed managing token costs, such as AJ Fisher's exploration of 'diffusion' models. Analogous to the diffusers used to generate images, they generate text at lighting speed, making them cheaper to operate while also being less accurate than the pricey and slower “autoregressive” #FrontierModels.

Fisher's solution? Use a low-quality model and make it iterate on a problem (that new classic, the #RalphWiggumLoop) until it gets a satisfactory solution. This approach delivers the same result as a full-fat model, for anywhere from one half to one tenth the spend. #Google released its #DiffusionGemma model, which produces text at prodigious speed, just days after Fisher's talk, giving everyone the ability to try this approach.” — #MarkPesce

#AI / #ArtificialIntelligence / #developers / #software / #RalphWiggens / #Simpsons <https://theregister.com/columnists/2026/06/17/developers-build-the-best-tools-for-developers-and-are-now-defanging-the-ai-menace/5255316>

“Now that organisations have been weaned off earlier 'all you can eat' #subscription plans and onto 'pay-as-you-go' metered #token consumption, they're all in various stages of sticker shock.

Several talks at the conference discussed managing token costs, such as AJ Fisher's exploration of 'diffusion' models. Analogous to the diffusers used to generate images, they generate text at lighting speed, making them cheaper to operate while also being less accurate than the pricey and slower “autoregressive” #FrontierModels.

Fisher's solution? Use a low-quality model and make it iterate on a problem (that new classic, the #RalphWiggumLoop) until it gets a satisfactory solution. This approach delivers the same result as a full-fat model, for anywhere from one half to one tenth the spend. #Google released its #DiffusionGemma model, which produces text at prodigious speed, just days after Fisher's talk, giving everyone the ability to try this approach.” — #MarkPesce

#AI / #ArtificialIntelligence / #developers / #software / #RalphWiggens / #Simpsons <https://theregister.com/columnists/2026/06/17/developers-build-the-best-tools-for-developers-and-are-now-defanging-the-ai-menace/5255316>

“Now that organisations have been weaned off earlier 'all you can eat' #subscription plans and onto 'pay-as-you-go' metered #token consumption, they're all in various stages of sticker shock.

Several talks at the conference discussed managing token costs, such as AJ Fisher's exploration of 'diffusion' models. Analogous to the diffusers used to generate images, they generate text at lighting speed, making them cheaper to operate while also being less accurate than the pricey and slower “autoregressive” #FrontierModels.

Fisher's solution? Use a low-quality model and make it iterate on a problem (that new classic, the #RalphWiggumLoop) until it gets a satisfactory solution. This approach delivers the same result as a full-fat model, for anywhere from one half to one tenth the spend. #Google released its #DiffusionGemma model, which produces text at prodigious speed, just days after Fisher's talk, giving everyone the ability to try this approach.” — #MarkPesce

#AI / #ArtificialIntelligence / #developers / #software / #RalphWiggens / #Simpsons <https://theregister.com/columnists/2026/06/17/developers-build-the-best-tools-for-developers-and-are-now-defanging-the-ai-menace/5255316>

“Now that organisations have been weaned off earlier 'all you can eat' #subscription plans and onto 'pay-as-you-go' metered #token consumption, they're all in various stages of sticker shock.

Several talks at the conference discussed managing token costs, such as AJ Fisher's exploration of 'diffusion' models. Analogous to the diffusers used to generate images, they generate text at lighting speed, making them cheaper to operate while also being less accurate than the pricey and slower “autoregressive” #FrontierModels.

Fisher's solution? Use a low-quality model and make it iterate on a problem (that new classic, the #RalphWiggumLoop) until it gets a satisfactory solution. This approach delivers the same result as a full-fat model, for anywhere from one half to one tenth the spend. #Google released its #DiffusionGemma model, which produces text at prodigious speed, just days after Fisher's talk, giving everyone the ability to try this approach.” — #MarkPesce

#AI / #ArtificialIntelligence / #developers / #software / #RalphWiggens / #Simpsons <https://theregister.com/columnists/2026/06/17/developers-build-the-best-tools-for-developers-and-are-now-defanging-the-ai-menace/5255316>

🧠 #Google ha presentato #DiffusionGemma, un nuovo modello open source sperimentale che esplora un approccio diverso alla generazione del testo. 

👉 I dettagli: https://www.linkedin.com/posts/alessiopomaro_google-diffusiongemma-gemma-ugcPost-7472241830621777921-CrTe/

___ 
✉️ 𝗦𝗲 𝘃𝘂𝗼𝗶 𝗿𝗶𝗺𝗮𝗻𝗲𝗿𝗲 𝗮𝗴𝗴𝗶𝗼𝗿𝗻𝗮𝘁𝗼/𝗮 𝘀𝘂 𝗾𝘂𝗲𝘀𝘁𝗲 𝘁𝗲𝗺𝗮𝘁𝗶𝗰𝗵𝗲, 𝗶𝘀𝗰𝗿𝗶𝘃𝗶𝘁𝗶 𝗮𝗹𝗹𝗮 𝗺𝗶𝗮 𝗻𝗲𝘄𝘀𝗹𝗲𝘁𝘁𝗲𝗿: https://bit.ly/newsletter-alessiopomaro

#AI #GenAI #GenerativeAI #IntelligenzaArtificiale #LLM 

🧠 #Google ha presentato #DiffusionGemma, un nuovo modello open source sperimentale che esplora un approccio diverso alla generazione del testo. 

👉 I dettagli: https://www.linkedin.com/posts/alessiopomaro_google-diffusiongemma-gemma-ugcPost-7472241830621777921-CrTe/

___ 
✉️ 𝗦𝗲 𝘃𝘂𝗼𝗶 𝗿𝗶𝗺𝗮𝗻𝗲𝗿𝗲 𝗮𝗴𝗴𝗶𝗼𝗿𝗻𝗮𝘁𝗼/𝗮 𝘀𝘂 𝗾𝘂𝗲𝘀𝘁𝗲 𝘁𝗲𝗺𝗮𝘁𝗶𝗰𝗵𝗲, 𝗶𝘀𝗰𝗿𝗶𝘃𝗶𝘁𝗶 𝗮𝗹𝗹𝗮 𝗺𝗶𝗮 𝗻𝗲𝘄𝘀𝗹𝗲𝘁𝘁𝗲𝗿: https://bit.ly/newsletter-alessiopomaro

#AI #GenAI #GenerativeAI #IntelligenzaArtificiale #LLM 

🧠 #Google ha presentato #DiffusionGemma, un nuovo modello open source sperimentale che esplora un approccio diverso alla generazione del testo. 

👉 I dettagli: https://www.linkedin.com/posts/alessiopomaro_google-diffusiongemma-gemma-ugcPost-7472241830621777921-CrTe/

___ 
✉️ 𝗦𝗲 𝘃𝘂𝗼𝗶 𝗿𝗶𝗺𝗮𝗻𝗲𝗿𝗲 𝗮𝗴𝗴𝗶𝗼𝗿𝗻𝗮𝘁𝗼/𝗮 𝘀𝘂 𝗾𝘂𝗲𝘀𝘁𝗲 𝘁𝗲𝗺𝗮𝘁𝗶𝗰𝗵𝗲, 𝗶𝘀𝗰𝗿𝗶𝘃𝗶𝘁𝗶 𝗮𝗹𝗹𝗮 𝗺𝗶𝗮 𝗻𝗲𝘄𝘀𝗹𝗲𝘁𝘁𝗲𝗿: https://bit.ly/newsletter-alessiopomaro

#AI #GenAI #GenerativeAI #IntelligenzaArtificiale #LLM 

🧠 #Google ha presentato #DiffusionGemma, un nuovo modello open source sperimentale che esplora un approccio diverso alla generazione del testo. 

👉 I dettagli: https://www.linkedin.com/posts/alessiopomaro_google-diffusiongemma-gemma-ugcPost-7472241830621777921-CrTe/

___ 
✉️ 𝗦𝗲 𝘃𝘂𝗼𝗶 𝗿𝗶𝗺𝗮𝗻𝗲𝗿𝗲 𝗮𝗴𝗴𝗶𝗼𝗿𝗻𝗮𝘁𝗼/𝗮 𝘀𝘂 𝗾𝘂𝗲𝘀𝘁𝗲 𝘁𝗲𝗺𝗮𝘁𝗶𝗰𝗵𝗲, 𝗶𝘀𝗰𝗿𝗶𝘃𝗶𝘁𝗶 𝗮𝗹𝗹𝗮 𝗺𝗶𝗮 𝗻𝗲𝘄𝘀𝗹𝗲𝘁𝘁𝗲𝗿: https://bit.ly/newsletter-alessiopomaro

#AI #GenAI #GenerativeAI #IntelligenzaArtificiale #LLM 

RT @LottoLabs: DiffusionGemma 26B-A4B mit llama.cpp-Fork. Dies ist ein gutes Beispiel dafür, wie Diffusionsmodelle einen Textblock parallel im Gegensatz zum nächsten Token generieren. Allerdings muss ich auf bessere Server-Unterstützung für llama.cpp warten oder zu vllm oder ktransformers wechseln, um tatsächliche Auswertungen etc. durchzuführen. Video.

mehr auf Arint.info

#AI #DiffusionGemma #DiffusionModels #ktransformers #llama #vllm #arint_info

https://x.com/LottoLabs/status/2064920298206728560#m

RT @LottoLabs: DiffusionGemma 26B-A4B mit llama.cpp-Fork. Dies ist ein gutes Beispiel dafür, wie Diffusionsmodelle einen Textblock parallel im Gegensatz zum nächsten Token generieren. Allerdings muss ich auf bessere Server-Unterstützung für llama.cpp warten oder zu vllm oder ktransformers wechseln, um tatsächliche Auswertungen etc. durchzuführen. Video.

mehr auf Arint.info

#AI #DiffusionGemma #DiffusionModels #ktransformers #llama #vllm #arint_info

https://x.com/LottoLabs/status/2064920298206728560#m

RT @LottoLabs: DiffusionGemma 26B-A4B mit llama.cpp-Fork. Dies ist ein gutes Beispiel dafür, wie Diffusionsmodelle einen Textblock parallel im Gegensatz zum nächsten Token generieren. Allerdings muss ich auf bessere Server-Unterstützung für llama.cpp warten oder zu vllm oder ktransformers wechseln, um tatsächliche Auswertungen etc. durchzuführen. Video.

mehr auf Arint.info

#AI #DiffusionGemma #DiffusionModels #ktransformers #llama #vllm #arint_info

https://x.com/LottoLabs/status/2064920298206728560#m

RT @LottoLabs: DiffusionGemma 26B-A4B mit llama.cpp-Fork. Dies ist ein gutes Beispiel dafür, wie Diffusionsmodelle einen Textblock parallel im Gegensatz zum nächsten Token generieren. Allerdings muss ich auf bessere Server-Unterstützung für llama.cpp warten oder zu vllm oder ktransformers wechseln, um tatsächliche Auswertungen etc. durchzuführen. Video.

mehr auf Arint.info

#AI #DiffusionGemma #DiffusionModels #ktransformers #llama #vllm #arint_info

https://x.com/LottoLabs/status/2064920298206728560#m

#AI at super speed: #Google's #DiffusionGemma

https://gadgetflux.eu/google-diffusiongemma-generare-text-4-mai-rapida/

#AI at super speed: #Google's #DiffusionGemma

https://gadgetflux.eu/google-diffusiongemma-generare-text-4-mai-rapida/

#AI at super speed: #Google's #DiffusionGemma

https://gadgetflux.eu/google-diffusiongemma-generare-text-4-mai-rapida/

#AI at super speed: #Google's #DiffusionGemma

https://gadgetflux.eu/google-diffusiongemma-generare-text-4-mai-rapida/

https://winbuzzer.com/2026/06/11/google-diffusiongemma-trades-quality-for-local-ai-speed-xcxwbn/

Google has introduced DiffusionGemma to speed local AI output through parallel text diffusion, but lower quality than Gemma 4 keeps trade-offs visible.

#AI #DiffusionGemma #TextDiffusion #Google #GoogleAI #AIModels #OpenSourceAI #OnDeviceAI #AIResearch

https://winbuzzer.com/2026/06/11/google-diffusiongemma-trades-quality-for-local-ai-speed-xcxwbn/

Google has introduced DiffusionGemma to speed local AI output through parallel text diffusion, but lower quality than Gemma 4 keeps trade-offs visible.

#AI #DiffusionGemma #TextDiffusion #Google #GoogleAI #AIModels #OpenSourceAI #OnDeviceAI #AIResearch

https://winbuzzer.com/2026/06/11/google-diffusiongemma-trades-quality-for-local-ai-speed-xcxwbn/

Google has introduced DiffusionGemma to speed local AI output through parallel text diffusion, but lower quality than Gemma 4 keeps trade-offs visible.

#AI #DiffusionGemma #TextDiffusion #Google #GoogleAI #AIModels #OpenSourceAI #OnDeviceAI #AIResearch

https://winbuzzer.com/2026/06/11/google-diffusiongemma-trades-quality-for-local-ai-speed-xcxwbn/

Google has introduced DiffusionGemma to speed local AI output through parallel text diffusion, but lower quality than Gemma 4 keeps trade-offs visible.

#AI #DiffusionGemma #TextDiffusion #Google #GoogleAI #AIModels #OpenSourceAI #OnDeviceAI #AIResearch

👀 DiffusionGemma: Google lancia un nuovo modello open source per esecuzione in locale che elabora 256 token in parallelo, usa attention bidirezionale e si auto-corregge in tempo reale.
https://gomoot.com/diffusiongemma-il-nuovo-modello-open-source-di-google/

#DiffusionGemma #geminidiffusion #google #news

👀 DiffusionGemma: Google lancia un nuovo modello open source per esecuzione in locale che elabora 256 token in parallelo, usa attention bidirezionale e si auto-corregge in tempo reale.
https://gomoot.com/diffusiongemma-il-nuovo-modello-open-source-di-google/

#DiffusionGemma #geminidiffusion #google #news

👀 DiffusionGemma: Google lancia un nuovo modello open source per esecuzione in locale che elabora 256 token in parallelo, usa attention bidirezionale e si auto-corregge in tempo reale.
https://gomoot.com/diffusiongemma-il-nuovo-modello-open-source-di-google/

#DiffusionGemma #geminidiffusion #google #news

Google veröffentlicht das Open-Source-Modell DiffusionGemma, das durch parallele Text-Diffusion auf lokalen Grafikkarten die Generierung beschleunigt.

Das 26B-Modell aktiviert 3,8B Parameter pro Abfrage und generiert 256 Token zeitgleich. Auf einer Nvidia RTX 5090 erreicht es über 700 Token/s. Die allgemeine Textqualität liegt jedoch unter der des autoregressiven Gemma-4-Modells.

#DiffusionGemma #Google #HuggingFace #OpenSource #AIGeneratedImage

https://www.all-ai.de/news/news26top/gemma-diffusion-schreiben

RT @googlegemma: Triff DiffusionGemma! Ein experimentelles Open-Source-Modell, das einen schnellen Ansatz zur Textgenerierung erforscht und unter der Apache 2.0-Lizenz veröffentlicht wurde. Es geht über sequenzielle, tokenweise Prozesse hinaus, um ganze Textblöcke gleichzeitig zu generieren. Hier ist, was bei DiffusionGemma neu ist: 👇 Video

mehr auf Arint.info

#Apache20 #DiffusionGemma #KI #MachineLearning #OpenSource #TextGenerierung #arint_info

https://x.com/googlegemma/status/2064741002204545467#m

Google、ローカルAIが4倍速くなるテキスト生成モデル「DiffusionGemma」を実験的に発表、逐次ではなく一括で生成／「GeForce RTX 5090」で700トークン/秒超を達成
https://forest.watch.impress.co.jp/docs/news/2116179.html

#forest_watch_impress #Gemma #Google_DeepMind #Gemma_4 #DiffusionGemma #genai #文章生成 #AIコーディング #Gemini

Google、ローカルAIが4倍速くなるテキスト生成モデル「DiffusionGemma」を実験的に発表、逐次ではなく一括で生成／「GeForce RTX 5090」で700トークン/秒超を達成
https://forest.watch.impress.co.jp/docs/news/2116179.html

#forest_watch_impress #Gemma #Google_DeepMind #Gemma_4 #DiffusionGemma #genai #文章生成 #AIコーディング #Gemini