Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Gemma 3 27B + Ollama + Open WebUI + M3 Ultra 🔥 What a model! Great release Google! 👏🏻

Ivan Fioravanti ᯅ

39,912 subscribers

60,764 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & Technologie Nachrichten & Politik

Anya Rossi• Live Now

Private livecam show

11 Kommentare

Profilbild von Ivan Fioravanti ᯅ

Ivan Fioravanti ᯅvor 1 Jahr

This model is INCREDIBLE! I love it!

Profilbild von Togoda AI Search Engine

Togoda AI Search Enginevor 1 Jahr

Togoda is Google on Steroids with AI summaries . 🚀 The only thematic AI search engine.👀 It's 100% private with third party proxy. 🧨 Try it today & experience the difference! 👉Follow us @togoda_com 👈 🚀Help us grow & share this post!🚀

Profilbild von 无逸 | Axelrod 𝕏

无逸 | Axelrod 𝕏vor 1 Jahr

what is the terminal in the video

Profilbild von Ivan Fioravanti ᯅ

Ivan Fioravanti ᯅvor 1 Jahr

iTerm 2. I play with it and Ghostty.

Profilbild von Christopher Großmann

Christopher Großmannvor 1 Jahr

It got an emotional breakdown when it catastrophically failed to create create an amazing animation using p5js… I just asked it to correct the error… 27B fp16… hilarious 😂

Profilbild von Flavio Adamo

Flavio Adamovor 1 Jahr

Ikr? I just switched my client local LLM from DeepSeek r1 32b to this one and the difference is huge.

Profilbild von Cavit Erginsoy

Cavit Erginsoyvor 1 Jahr

What’s that frontend you’re using?

Profilbild von Arthur Lee

Arthur Leevor 1 Jahr

Totally agree - awesome model!

Profilbild von Mark Ankcorn

Mark Ankcornvor 1 Jahr

I’m only getting 14 tk/s when I run the MLX version in LM Studio. Seems faster for you

Profilbild von Ivan Fioravanti ᯅ

Ivan Fioravanti ᯅvor 1 Jahr

I used Ollama with the Q4 version here.

Profilbild von Bala Menon

Bala Menonvor 1 Jahr

I've tried everything to improve the time to first token on this running on Apple Silicon but something's amiss. Your demo also shows that. Not sure how to optimize it.

Ähnliche Videos

Gemma 3 + Ollama + N8N + Open Router 🔥 What a model! Great release Google! 👏🏻 - Runs locally via Ollama - Outperforms Claude Mini & DeepSeek - Available in 1B, 4B, 12B & 27B sizes - 128k context window - Free API access Save this video it will save you hundreds on AI costs. 🚀 Want the SOP? DM me.

Gemma 3 + Ollama + N8N + Open Router 🔥 What a model! Great release Google! 👏🏻 - Runs locally via Ollama - Outperforms Claude Mini & DeepSeek - Available in 1B, 4B, 12B & 27B sizes - 128k context window - Free API access Save this video it will save you hundreds on AI costs. 🚀 Want the SOP? DM me.

Julian Goldie SEO

140,545 Aufrufe • vor 1 Jahr

Ollama WebUI is amazing. Download with Docker, choose your open-source model, customize it without writing a single line of code.

Ollama WebUI is amazing. Download with Docker, choose your open-source model, customize it without writing a single line of code.

Muratcan Koylan

149,118 Aufrufe • vor 2 Jahren

🚨 Google Just Made OpenClaw Free (GEMMA 4): 0:00 - Why Gemma 4 matters 0:48 - #3 open model in the world 1:24 - What Gemma 4 actually does 2:01 - What this means for OpenClaw 3:03 - How to set up Gemma 4 3:58 - My honest take after running Claude for 3 months

🚨 Google Just Made OpenClaw Free (GEMMA 4): 0:00 - Why Gemma 4 matters 0:48 - #3 open model in the world 1:24 - What Gemma 4 actually does 2:01 - What this means for OpenClaw 3:03 - How to set up Gemma 4 3:58 - My honest take after running Claude for 3 months

Sharbel

368,986 Aufrufe • vor 5 Monaten

3️⃣ ways to run Gemma 3. Get a Gemma model up and running fast using Keras, Ollama, and the GenAI SDK in this demo from Developer Relations Engineer Marina Coelho.

3️⃣ ways to run Gemma 3. Get a Gemma model up and running fast using Keras, Ollama, and the GenAI SDK in this demo from Developer Relations Engineer Marina Coelho.

Google AI Developers

25,192 Aufrufe • vor 1 Jahr

See what’s new in Gemma 3, the latest generation of open models from Google with sizes ranging from 1B to 27B parameters. These versatile models run quickly and efficiently, and scale to developer needs to provide project flexibility.

See what’s new in Gemma 3, the latest generation of open models from Google with sizes ranging from 1B to 27B parameters. These versatile models run quickly and efficiently, and scale to developer needs to provide project flexibility.

Google AI Developers

11,482 Aufrufe • vor 1 Jahr

This is MiniMax-M2.5 MLX running in LM Studio on an Apple Mac Studio M3 Ultra 512GB. Fast enough out of the box for hosting OpenClaw, n8n workflows, and Open WebUI for the team.

This is MiniMax-M2.5 MLX running in LM Studio on an Apple Mac Studio M3 Ultra 512GB. Fast enough out of the box for hosting OpenClaw, n8n workflows, and Open WebUI for the team.

Patrick J Kennedy

76,574 Aufrufe • vor 7 Monaten

$GOOGL launched Gemma 4 which is its newest open model family built for reasoning, multimodal tasks, agentic workflows & efficient on-device use. The release adds long context, code generation & support for 140+ languages as Google keeps expanding its open model ecosystem.

$GOOGL launched Gemma 4 which is its newest open model family built for reasoning, multimodal tasks, agentic workflows & efficient on-device use. The release adds long context, code generation & support for 140+ languages as Google keeps expanding its open model ecosystem.

Shay Boloor

72,509 Aufrufe • vor 5 Monaten

Few seconds and <4GB to full fine tune Gemma 3 270M for classification tasks! Here on M3 Ultra! I'll keep experimenting and checking final result! base model, batch size 4, adaw (testing with adafactor too!), rank 128. Video at normal speed here! 🔥

Few seconds and <4GB to full fine tune Gemma 3 270M for classification tasks! Here on M3 Ultra! I'll keep experimenting and checking final result! base model, batch size 4, adaw (testing with adafactor too!), rank 128. Video at normal speed here! 🔥

Ivan Fioravanti ᯅ

35,282 Aufrufe • vor 1 Jahr

A fully offline translator, built with Google Gemma 4, Google Antigravity, and a Raspberry Pi 5. 🛠️ The Gemma Translator is a portable AI experiment with a custom interface, printed case, and wired electronics, powered by the smallest Gemma model. Build your own →

A fully offline translator, built with Google Gemma 4, Google Antigravity, and a Raspberry Pi 5. 🛠️ The Gemma Translator is a portable AI experiment with a custom interface, printed case, and wired electronics, powered by the smallest Gemma model. Build your own →

Google for Developers

78,939 Aufrufe • vor 1 Monat

the era of agentic AI is here Google just open sourced Gemma 3, you can run it on a single GPU laptop or even phone - agentic AI workflows - 4 Sizes – 1B, 4B, 12B, 27B - up to 128K tokens - speaks 140+ languages - hit 1338 ELO on LMArena try & download for free, links 👇

the era of agentic AI is here Google just open sourced Gemma 3, you can run it on a single GPU laptop or even phone - agentic AI workflows - 4 Sizes – 1B, 4B, 12B, 27B - up to 128K tokens - speaks 140+ languages - hit 1338 ELO on LMArena try & download for free, links 👇

el.cine

199,579 Aufrufe • vor 1 Jahr

What is this Nanbeige4.1-3B model running at - 77 toks/s in bf16 (in video) - 115 toks/s in 8bit on M3 Ultra with MLX with these benchmark scores! 🔥

What is this Nanbeige4.1-3B model running at - 77 toks/s in bf16 (in video) - 115 toks/s in 8bit on M3 Ultra with MLX with these benchmark scores! 🔥

Ivan Fioravanti ᯅ

85,228 Aufrufe • vor 7 Monaten

𝗚𝗲𝗺𝗺𝗮 𝟰 + 𝗢𝗹𝗹𝗮𝗺𝗮 + 𝗢𝗽𝗲𝗻𝗖𝗹𝗮𝘄 𝗶𝘀 𝗮 𝗳𝘂𝗹𝗹𝘆 𝗹𝗼𝗰𝗮𝗹 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁 𝘁𝗵𝗮𝘁 𝗿𝘂𝗻𝘀 𝗳𝗿𝗲𝗲 𝗳𝗼𝗿𝗲𝘃𝗲𝗿. #3 open model in the world. Runs on your laptop. Zero API costs. Zero data leaving your machine. Setup in 3 steps: → Install Ollama and run "ollama pull gemma4" — downloads the model → Install OpenClaw and select Ollama as your provider → Connect Telegram — message your agent from anywhere, completely local One prompt built a working SEO calculator — HTML, CSS, JavaScript, no debugging. Coding benchmark jumped from 110 to 2,150 vs the previous Gemma. Apache 2.0. No restrictions. No monthly bill. No surprises. Want the full setup guide? DM me.

𝗚𝗲𝗺𝗺𝗮 𝟰 + 𝗢𝗹𝗹𝗮𝗺𝗮 + 𝗢𝗽𝗲𝗻𝗖𝗹𝗮𝘄 𝗶𝘀 𝗮 𝗳𝘂𝗹𝗹𝘆 𝗹𝗼𝗰𝗮𝗹 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁 𝘁𝗵𝗮𝘁 𝗿𝘂𝗻𝘀 𝗳𝗿𝗲𝗲 𝗳𝗼𝗿𝗲𝘃𝗲𝗿. #3 open model in the world. Runs on your laptop. Zero API costs. Zero data leaving your machine. Setup in 3 steps: → Install Ollama and run "ollama pull gemma4" — downloads the model → Install OpenClaw and select Ollama as your provider → Connect Telegram — message your agent from anywhere, completely local One prompt built a working SEO calculator — HTML, CSS, JavaScript, no debugging. Coding benchmark jumped from 110 to 2,150 vs the previous Gemma. Apache 2.0. No restrictions. No monthly bill. No surprises. Want the full setup guide? DM me.

Julian Goldie SEO

77,202 Aufrufe • vor 5 Monaten

Jensen on Nemotron 3 Ultra and it's role in the open ecosystem. It's great to have Nvidia leading on this, with so much turnover in open model providers in recent years. Super excited to see how the model turns out.

Jensen on Nemotron 3 Ultra and it's role in the open ecosystem. It's great to have Nvidia leading on this, with so much turnover in open model providers in recent years. Super excited to see how the model turns out.

Nathan Lambert

26,650 Aufrufe • vor 6 Monaten

Gemma 3 100% Local using ollama and Chainlit Create an Application DEMO: 👇 🚀 27B, 12B, 4B, 1B 🌐 140+ languages supported 📊 128K context window 🖼️ Multimodal capabilities 🏆 Outperforms Llama 405B, DeepSeek V3 💻 Runs on single GPU 🤖 Enables function calling 🔍 Vision understanding capability 🧠 14T training tokens 🔄 5:1 local-global ratio 📱 Local processing possible 🎯 67.5 MMLU-Pro score 🏅 133 Elo score 📦 Int4 quantisation support Google AI Google DeepMind Sundar Pichai

Gemma 3 100% Local using ollama and Chainlit Create an Application DEMO: 👇 🚀 27B, 12B, 4B, 1B 🌐 140+ languages supported 📊 128K context window 🖼️ Multimodal capabilities 🏆 Outperforms Llama 405B, DeepSeek V3 💻 Runs on single GPU 🤖 Enables function calling 🔍 Vision understanding capability 🧠 14T training tokens 🔄 5:1 local-global ratio 📱 Local processing possible 🎯 67.5 MMLU-Pro score 🏅 133 Elo score 📦 Int4 quantisation support Google AI Google DeepMind Sundar Pichai

Mervin Praison

26,358 Aufrufe • vor 1 Jahr

Artifacts, but 100% Open Source, Private & Local. Open WebUI has released a game changer update---"Artifacts". Instead of proprietary LLMs, you can now use fully LOCAL and PRIVATE LLM via ollama to build apps! Here I use Qwen 2.5 32B to build a game of life app.

Artifacts, but 100% Open Source, Private & Local. Open WebUI has released a game changer update---"Artifacts". Instead of proprietary LLMs, you can now use fully LOCAL and PRIVATE LLM via ollama to build apps! Here I use Qwen 2.5 32B to build a game of life app.

cocktail peanut

60,233 Aufrufe • vor 1 Jahr

Claude Code is now completely free forever 🤯 Just connect it to Ollama and run a local model like Google’s new Gemma 4. That means Claude Code agents can run directly on your computer with zero API bills and zero subscriptions. Google may have just ended AI subscription fees for good. 🚀

Claude Code is now completely free forever 🤯 Just connect it to Ollama and run a local model like Google’s new Gemma 4. That means Claude Code agents can run directly on your computer with zero API bills and zero subscriptions. Google may have just ended AI subscription fees for good. 🚀

Julian Goldie SEO

10,098 Aufrufe • vor 5 Monaten

A long time coming but new mlx-lm is here with better batching support in the server and Gemma 4. pip install -U mlx-lm Here is a video where a single M3 Ultra serves 5 opencode sessions with Gemma 4 26B that process ~130k tokens in ~1.5 minutes.

A long time coming but new mlx-lm is here with better batching support in the server and Gemma 4. pip install -U mlx-lm Here is a video where a single M3 Ultra serves 5 opencode sessions with Gemma 4 26B that process ~130k tokens in ~1.5 minutes.

Angelos Katharopoulos

66,202 Aufrufe • vor 5 Monaten

At Google I/O, I sat down with Omar Sanseviero and 👩‍💻 Paige Bailey from Google DeepMind to talk about Gemma, open models, AI Studio, on-device AI, sovereign AI and the future of AI development. A great conversation on how building with AI is becoming more open, local and accessible.

At Google I/O, I sat down with Omar Sanseviero and 👩‍💻 Paige Bailey from Google DeepMind to talk about Gemma, open models, AI Studio, on-device AI, sovereign AI and the future of AI development. A great conversation on how building with AI is becoming more open, local and accessible.

Chubby♨️

13,741 Aufrufe • vor 3 Monaten