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.

Here’s Deepseek r1 1.5B thinking through a problem — it’s comparable to 4o and Claude 3.5 Sonnet in a number of domains like math. Except… it’s a 1.5B model… and can run on virtually any hardware. Truly a huge efficiency leap.

Aaron Ng

35,863 subscribers

564,677 views • 1 year ago •via X (Twitter)

Education Arts Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

it's crazy what a 1.5B model can do these days! "VibeThinker-1.5B is a 1.5-billion parameter dense language model. With a total training cost of only $7,800 USD, it achieves reasoning performance comparable to larger models like GPT OSS-20B Medium." runs perfectly on device!

it's crazy what a 1.5B model can do these days! "VibeThinker-1.5B is a 1.5-billion parameter dense language model. With a total training cost of only $7,800 USD, it achieves reasoning performance comparable to larger models like GPT OSS-20B Medium." runs perfectly on device!

Maziyar PANAHI

202,305 views • 7 months ago

Perplexity's Sonar—built on Llama 3.3 70b—outperforms GPT-4o-mini and Claude 3.5 Haiku while matching or surpassing top models like GPT-4o and Claude 3.5 Sonnet in user satisfaction. At 1200 tokens/second, Sonar is optimized for answer quality and speed.

Perplexity's Sonar—built on Llama 3.3 70b—outperforms GPT-4o-mini and Claude 3.5 Haiku while matching or surpassing top models like GPT-4o and Claude 3.5 Sonnet in user satisfaction. At 1200 tokens/second, Sonar is optimized for answer quality and speed.

Perplexity

565,953 views • 1 year ago

Llama 4 seems to actually be a poor model for coding. Scout (109B) and Maverick (402B) underperform 4o, Gemini Flash, Grok 3, DeepSeek V3 and Sonnet 3.5/7 on the Kscores benchmark which tests on coding tasks like this. ELO-maxxing on LMarena doesn’t create the best models.

Llama 4 seems to actually be a poor model for coding. Scout (109B) and Maverick (402B) underperform 4o, Gemini Flash, Grok 3, DeepSeek V3 and Sonnet 3.5/7 on the Kscores benchmark which tests on coding tasks like this. ELO-maxxing on LMarena doesn’t create the best models.

Deedy

252,791 views • 1 year ago

Google JUST dropped Gemini 2.5 Pro their "most intelligent AI model yet". This new "thinking model" tops LMArena by a significant margin and crushes DeepSeek-R1, Grok 3 and Claude 3.7 in math, science and coding benchmarks. Ships with 1M token context (2M coming), can process multimodal data, and is vibe coding approved to the point that it can build entire games from a single prompt.

Google JUST dropped Gemini 2.5 Pro their "most intelligent AI model yet". This new "thinking model" tops LMArena by a significant margin and crushes DeepSeek-R1, Grok 3 and Claude 3.7 in math, science and coding benchmarks. Ships with 1M token context (2M coming), can process multimodal data, and is vibe coding approved to the point that it can build entire games from a single prompt.

Bilawal Sidhu

34,944 views • 1 year ago

DeepSeek R1 distilled to Qwen 1.5B easily runs on my iPhone 16 with MLX swift. Here's the 4-bit model reasoning entirely on device at almost 60 toks/sec:

DeepSeek R1 distilled to Qwen 1.5B easily runs on my iPhone 16 with MLX swift. Here's the 4-bit model reasoning entirely on device at almost 60 toks/sec:

Awni Hannun

1,139,656 views • 1 year ago

fullmoon v1.2.0 is now available on the App Store so you can reason free, locally, and privately on all of your devices - adds DeepSeek-R1-Distill-Qwen-1.5B - completely free and open source - works on iPhone, iPad, Mac, and Vision

fullmoon v1.2.0 is now available on the App Store so you can reason free, locally, and privately on all of your devices - adds DeepSeek-R1-Distill-Qwen-1.5B - completely free and open source - works on iPhone, iPad, Mac, and Vision

fullmoon

36,279 views • 1 year ago

This is amazing! Someone trained a 1.5B model (with GRPO) to solve mazes! model:

This is amazing! Someone trained a 1.5B model (with GRPO) to solve mazes! model:

Victor M

139,407 views • 1 year ago

Previews are now available on the Poe iOS app! Generate custom interactive apps directly in chat using any of the leading LLMs, including Claude 3.5 Sonnet, GPT-4o, Gemini 1.5 Pro, and Llama 3.1 405b. (1/4)

Previews are now available on the Poe iOS app! Generate custom interactive apps directly in chat using any of the leading LLMs, including Claude 3.5 Sonnet, GPT-4o, Gemini 1.5 Pro, and Llama 3.1 405b. (1/4)

Poe

38,866 views • 1 year ago

DeepSeek R1 is *the* best model available right now. It's at the level of o1, but you can use it for free, and it's much faster. A huge leap forward that nobody saw coming. No wonder so many people are throwing tantrums online trying to discredit the Chinese students who built this. You can use DeepSeek in Visual Studio Code right now: 1. Install the Qodo Gen AI extension 2. Select DeepSeek R1 from their list of models The Qodo team is hosting DeepSeek on their servers, so none of your data will go to China. I've been building a Tetris game using DeepSeek, and this is the most impressive model I've seen so far.

DeepSeek R1 is the best model available right now. It's at the level of o1, but you can use it for free, and it's much faster. A huge leap forward that nobody saw coming. No wonder so many people are throwing tantrums online trying to discredit the Chinese students who built this. You can use DeepSeek in Visual Studio Code right now: 1. Install the Qodo Gen AI extension 2. Select DeepSeek R1 from their list of models The Qodo team is hosting DeepSeek on their servers, so none of your data will go to China. I've been building a Tetris game using DeepSeek, and this is the most impressive model I've seen so far.

Santiago

1,223,957 views • 1 year ago

We just launched Claude Sonnet 4.5 and “Imagine with Claude”, a 5-day preview that creates dynamic experiences for you in real-time (and the first product I’ve worked on at Anthropic!). It pioneers the concept of “model-as-backend”, using a model to not only generate interfaces on the fly but also power all the functionality behind it – all made possible by our newest model, Claude Sonnet 4.5. Here’s a "choose your own adventure" version of my founder journey, as retold by Imagine with Claude:

We just launched Claude Sonnet 4.5 and “Imagine with Claude”, a 5-day preview that creates dynamic experiences for you in real-time (and the first product I’ve worked on at Anthropic!). It pioneers the concept of “model-as-backend”, using a model to not only generate interfaces on the fly but also power all the functionality behind it – all made possible by our newest model, Claude Sonnet 4.5. Here’s a "choose your own adventure" version of my founder journey, as retold by Imagine with Claude:

Sean Strong

115,687 views • 8 months ago

Llama 3.1 Nemotron 70B is the latest model from NVIDIA, released only a few hours ago. Initial testing shows the model outperforms GPT-4o and Sonnet 3.5 on several benchmarks. Try it on Akash Chat for free:

Llama 3.1 Nemotron 70B is the latest model from NVIDIA, released only a few hours ago. Initial testing shows the model outperforms GPT-4o and Sonnet 3.5 on several benchmarks. Try it on Akash Chat for free:

Akash Network

38,472 views • 1 year ago

Mumbai Billionaire with a net worth of $1.5B, takes the train to save time and beat the traffic

Mumbai Billionaire with a net worth of $1.5B, takes the train to save time and beat the traffic

Historic Vids

22,444,299 views • 2 years ago

Free 3.5 to a random like and RT! Pick any flavor It’s been a min. SN: this raspberry uncrustable taste amazing 🔥🔥🔥

Free 3.5 to a random like and RT! Pick any flavor It’s been a min. SN: this raspberry uncrustable taste amazing 🔥🔥🔥

10 toes 🏃🏾‍♂️💰

72,347 views • 9 months ago

If it’s outdoors, they just need to climb a slanted roof. If it’s indoors, any clown can Naruto-run straight through the gates.

If it’s outdoors, they just need to climb a slanted roof. If it’s indoors, any clown can Naruto-run straight through the gates.

Rothmus 🏴

20,348 views • 1 month ago

I’m not saying an open-source model you can run on consumer hardware is better than ChatGPT, just that sometimes it’s worth trying both. Prompt: “A zebra with a volcanic eruption in the background.”

I’m not saying an open-source model you can run on consumer hardware is better than ChatGPT, just that sometimes it’s worth trying both. Prompt: “A zebra with a volcanic eruption in the background.”

Victor M

105,328 views • 6 months ago

Jan v0.5.15: You can now tweak llama.cpp settings, and add any cloud model! Highlights 🎉 - Improved llama.cpp settings - Install & use any cloud model - Better hardware controls - New models: DeepSeek, Gemini, o3-mini, R1 distills Update your Jan or download the latest.

Jan v0.5.15: You can now tweak llama.cpp settings, and add any cloud model! Highlights 🎉 - Improved llama.cpp settings - Install & use any cloud model - Better hardware controls - New models: DeepSeek, Gemini, o3-mini, R1 distills Update your Jan or download the latest.

👋 Jan

11,062 views • 1 year ago

💬 "It’s a beautiful day, especially for me, because that’s a big number and it’s a huge privilege to be where I am." Mikel Arteta reflects on returning to winning ways in the Premier League 👇

💬 "It’s a beautiful day, especially for me, because that’s a big number and it’s a huge privilege to be where I am." Mikel Arteta reflects on returning to winning ways in the Premier League 👇

Arsenal

131,454 views • 1 year ago

Qwen has just released a model on par with GPT-4o... And you can run it locally easily 🤯 Yep. GPT-4o level AI running offline on a laptop. - Fully open source - Only 3B active parameters - 262k context length natively Quick steps to run it on your machine and details below

Qwen has just released a model on par with GPT-4o... And you can run it locally easily 🤯 Yep. GPT-4o level AI running offline on a laptop. - Fully open source - Only 3B active parameters - 262k context length natively Quick steps to run it on your machine and details below

Paul Couvert

503,787 views • 10 months ago