Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Ollama can now think! 🤔🤔🤔 For thinking models, and especially useful for very thoughtful models like DeepSeek-R1-0528, Ollama can separate the thoughts and the response. Thinking can also be disabled! This is useful for getting a direct response. This works across Ollama's CLI, API, and Python/JavaScript libraries. 🧵 blog... show more

ollama

167,882 subscribers

106,228 views • 1 year ago •via X (Twitter)

News & Politics Science & Technology Education

Anya Rossi• Live Now

Private livecam show

10 Comments

ollama1 year ago

Blog post: Models to try: DeepSeek-R1-0528 8B distilled ollama pull deepseek-r1:8b Qwen3 ollama pull qwen3

Somi1 year ago

Thinking thinking thinking 💭 Ollama!

ollama1 year ago

trying trying trying 💬 Ollama! 😂😂😂

P4mui 1 year ago

Oooooh ollama with R1-0528? I need to test that

ollama1 year ago

🫡

Frostyflakes1 year ago

Is this model dependant or can i use across smaller LLMs e.g. Gemma 2b? - So persons with lower hardware requirements can still enjoy this new feature with lower compute reqs

Tom Davenport1 year ago

Very good ollama 🥕

ollama1 year ago

🥕🥕🥕

Yakin Rubaiyat1 year ago

Nice work

bandr ☁️1 year ago

THANK you, that’s so helpful. R1 0528 is the best.

Related Videos

Ollama 0.2 is here! Concurrency is now enabled by default. This unlocks 2 major features: Parallel requests Ollama can now serve multiple requests at the same time, using only a little bit of additional memory for each request. This enables use cases such as: - Handling multiple chat sessions at the same time - Hosting code completion LLMs for your team - Processing different parts of a document simultaneously - Running multiple agents at the same time Run multiple models Ollama now supports loading different models at the same time. This improves several use cases: - Retrieval Augmented Generation (RAG): both the embedding and text completion models can be loaded into memory simultaneously. - Agents: multiple versions of an agent can now run simultaneously - Running large and small models side-by-side Models are automatically loaded and unloaded based on requests and how much GPU memory is available.

Ollama 0.2 is here! Concurrency is now enabled by default. This unlocks 2 major features: Parallel requests Ollama can now serve multiple requests at the same time, using only a little bit of additional memory for each request. This enables use cases such as: - Handling multiple chat sessions at the same time - Hosting code completion LLMs for your team - Processing different parts of a document simultaneously - Running multiple agents at the same time Run multiple models Ollama now supports loading different models at the same time. This improves several use cases: - Retrieval Augmented Generation (RAG): both the embedding and text completion models can be loaded into memory simultaneously. - Agents: multiple versions of an agent can now run simultaneously - Running large and small models side-by-side Models are automatically loaded and unloaded based on requests and how much GPU memory is available.

ollama

219,398 views • 2 years ago

Jeffrey Morgan was on TBPN this week to discuss Ollama's Series B fundraise and why open models are quickly becoming the default choice for developers Full video:

Jeffrey Morgan was on TBPN this week to discuss Ollama's Series B fundraise and why open models are quickly becoming the default choice for developers Full video:

ollama

33,801 views • 2 days ago

Ollama can now launch Pi, a minimal coding agent which you can customize for your workflow ollama launch pi You can even ask pi to write extensions for itself

Ollama can now launch Pi, a minimal coding agent which you can customize for your workflow ollama launch pi You can even ask pi to write extensions for itself

ollama

190,618 views • 4 months ago

Ollama now supports subagents and web search in Claude Code! Subagents can run tasks in parallel, such as file search, code exploration, and research, each in their own context. No MCP servers to configure or API keys required. Try it with any model on Ollama's cloud: ollama launch claude --model minimax-m2.5:cloud

Ollama now supports subagents and web search in Claude Code! Subagents can run tasks in parallel, such as file search, code exploration, and research, each in their own context. No MCP servers to configure or API keys required. Try it with any model on Ollama's cloud: ollama launch claude --model minimax-m2.5:cloud

ollama

84,101 views • 4 months ago

Ollama 0.17 makes it much simpler to use open models with OpenClaw🦞 Try it with: ollama launch openclaw Tutorial post in 🧵

Ollama 0.17 makes it much simpler to use open models with OpenClaw🦞 Try it with: ollama launch openclaw Tutorial post in 🧵

ollama

201,376 views • 4 months ago

Ollama can now run subagents in OpenCode Parallelize tasks which require longer context windows like research, refactoring, and code reviews ollama launch opencode

Ollama can now run subagents in OpenCode Parallelize tasks which require longer context windows like research, refactoring, and code reviews ollama launch opencode

ollama

126,094 views • 4 months ago

Ollama v0.8 is here! Now it can stream responses with tool calling! Example of Ollama doing web search:

Ollama v0.8 is here! Now it can stream responses with tool calling! Example of Ollama doing web search:

ollama

148,262 views • 1 year ago

The future of AI is open-source. And ollama is the easiest way to build AI applications with open-source LLMs. Here's how to build a free, private RAG app using open-source tools. We'll use: - Ollama for LLMs and embedding models - PostgreSQL for data storage and retrieval - pgai Vectorizer for embedding creation and sync (I use Nomic for embeddings and tinnyllama as my LLM but you can substitute them for any models on Ollama)

The future of AI is open-source. And ollama is the easiest way to build AI applications with open-source LLMs. Here's how to build a free, private RAG app using open-source tools. We'll use: - Ollama for LLMs and embedding models - PostgreSQL for data storage and retrieval - pgai Vectorizer for embedding creation and sync (I use Nomic for embeddings and tinnyllama as my LLM but you can substitute them for any models on Ollama)

Avthar

34,261 views • 1 year ago

This person says...👇👇👇 " I'm going to start suing ANYONE for emotional damage and distress for calling me he, him, bro sir,mister,brother is automatically gonna get you sued." 🤔🤔 What your response to him? 🧐

This person says...👇👇👇 " I'm going to start suing ANYONE for emotional damage and distress for calling me he, him, bro sir,mister,brother is automatically gonna get you sued." 🤔🤔 What your response to him? 🧐

Jannine.. #MagaMemeQueen ™️ 👑🇺🇸

48,042 views • 2 months ago

Hot tip for anyone doing AI dev: Use Ollama to easily run models like Deepseek-r1 or Gemma locally on your machine. It downloads them and spins up a server with an OpenAI SDK compatible API The smaller models are fast and good enough to work on new features or debug streaming without having to pay for API requests

Hot tip for anyone doing AI dev: Use Ollama to easily run models like Deepseek-r1 or Gemma locally on your machine. It downloads them and spins up a server with an OpenAI SDK compatible API The smaller models are fast and good enough to work on new features or debug streaming without having to pay for API requests

Wes Bos

153,435 views • 1 year ago

🚨BREAKING: OpenAI's Codex is now completely FREE to run locally with Ollama. No API costs. No rate limits. 100% private on your machine. You can now use both the Codex App and Codex CLI with powerful open-source models like DeepSeek V4, Gemma 4, and Qwen 3.6. Here's how to set it up in minutes:

🚨BREAKING: OpenAI's Codex is now completely FREE to run locally with Ollama. No API costs. No rate limits. 100% private on your machine. You can now use both the Codex App and Codex CLI with powerful open-source models like DeepSeek V4, Gemma 4, and Qwen 3.6. Here's how to set it up in minutes:

WorldofAI

809,096 views • 1 month ago

A puzzler for the masses. How intelligent are you? Thinking 🤔 is required. Unfortunately, not everyone can figure this out.

A puzzler for the masses. How intelligent are you? Thinking 🤔 is required. Unfortunately, not everyone can figure this out.

🌸𝓐𝓾𝓭𝓻𝓮𝔂🌸

15,454 views • 4 months ago

Canvas from Spine AI is an unlimited visual workspace for AI — where you can think, branch, and collaborate across hundreds of models. Chat works for Q&A. Canvas is for thinking. Congrats on the launch Akshay Budhkar & Ashwin V Raman!

Canvas from Spine AI is an unlimited visual workspace for AI — where you can think, branch, and collaborate across hundreds of models. Chat works for Q&A. Canvas is for thinking. Congrats on the launch Akshay Budhkar & Ashwin V Raman!

Y Combinator

15,891 views • 9 months ago

🚨 DeepSeek just dropped DeepSeek R1-0528 and it's INSANE for coding Built an entire game with Nebius Studio in three turn. The improvement from previous versions is wild. - API access available - Safe to use If this is R1... DeepSeek R2 is going to be absolutely nuts. How to access 👇 1/3

🚨 DeepSeek just dropped DeepSeek R1-0528 and it's INSANE for coding Built an entire game with Nebius Studio in three turn. The improvement from previous versions is wild. - API access available - Safe to use If this is R1... DeepSeek R2 is going to be absolutely nuts. How to access 👇 1/3

AshutoshShrivastava

61,058 views • 1 year ago

The Copilot CLI now supports builtin subagents for parallelizing search and coding tasks within separate context windows. Uniquely, the outer agent can invoke different models. Ask Opus, Codex, Gemini and a dozen other models for answers in parallel.

The Copilot CLI now supports builtin subagents for parallelizing search and coding tasks within separate context windows. Uniquely, the outer agent can invoke different models. Ask Opus, Codex, Gemini and a dozen other models for answers in parallel.

Evan Boyle

10,602 views • 6 months ago

✨Spotlight: Top 4 Code Arena open models Open models are moving fast, and this community is directly shaping how that progress shows up in real use. Your builds, votes, and experiments surface what frontier models can actually do in practice. To celebrate the momentum, we’re spotlighting the top open models in Code Arena (WebDev) 🧵👇 🔥 MiniMax (official) — MiniMax-M2.1 🤖 Z.ai — GLM-4.7 ✨ DeepSeek — Deepseek-v3.2-thinking 🚀 Xiaomi MiMo — Mimo-v2-flash (non-thinking) Let’s keep building in the open and raising the bar together 🚀

✨Spotlight: Top 4 Code Arena open models Open models are moving fast, and this community is directly shaping how that progress shows up in real use. Your builds, votes, and experiments surface what frontier models can actually do in practice. To celebrate the momentum, we’re spotlighting the top open models in Code Arena (WebDev) 🧵👇 🔥 MiniMax (official) — MiniMax-M2.1 🤖 Z.ai — GLM-4.7 ✨ DeepSeek — Deepseek-v3.2-thinking 🚀 Xiaomi MiMo — Mimo-v2-flash (non-thinking) Let’s keep building in the open and raising the bar together 🚀

Arena.ai

16,742 views • 6 months ago

Me and the wife are currently thinking on our Halloween costume for this year 🎃 Any suggestions on how we can top last year?? 🤔

Me and the wife are currently thinking on our Halloween costume for this year 🎃 Any suggestions on how we can top last year?? 🤔

Ludacris

74,942 views • 1 year ago

One easy way to create holes in 3D models, is by using a black and white texture. This is especially useful for cloth objects. However you can also turn it into geometry with thickness for 3D printing, with just a few modifiers. #Blender #b3d #Blender3D

One easy way to create holes in 3D models, is by using a black and white texture. This is especially useful for cloth objects. However you can also turn it into geometry with thickness for 3D printing, with just a few modifiers. #Blender #b3d #Blender3D

Jan van den Hemel

61,597 views • 8 months ago

Chrome Dev Tools 💡 You may not know that we can override response headers in Chrome Dev Tools 🤩 This can be very handy for handling CORS errors locally until they get fixed from the API server ✅👇

Chrome Dev Tools 💡 You may not know that we can override response headers in Chrome Dev Tools 🤩 This can be very handy for handling CORS errors locally until they get fixed from the API server ✅👇

Shripal Soni

24,460 views • 2 years ago