#diffusiongemma — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #diffusiongemma, aggregated by home.social.
-
“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 -
🧠 #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 -
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
-
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://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/ -
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
