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.

Today we’re announcing our “ThinkingCap” efficient model series with a 2× thinking token reduction on average in Qwen 3.6 27B, with up to 10x faster generation on individual examples.

Jaroslav Beck

17,957 subscribers

50,546 views • 2 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Managed to get QWEN 3.6 27B running in Cursor with localhost (no Ngrok) at 120 - 140 TPS on 2x 3090s.

Managed to get QWEN 3.6 27B running in Cursor with localhost (no Ngrok) at 120 - 140 TPS on 2x 3090s.

Youssof Al Toukhi

21,008 views • 3 months ago

I put Qwen 3.6 27B on a B200 for the fun of it. I told Fable to apply my past optimisation principles. Result? 1000 TPS Qwen 3.6 27B NVFP4 (550 TPS average long decode) I used the same principles that got me 250 TPS on 2x 3090s. Now I need to buy a DGX Station 🤪.

I put Qwen 3.6 27B on a B200 for the fun of it. I told Fable to apply my past optimisation principles. Result? 1000 TPS Qwen 3.6 27B NVFP4 (550 TPS average long decode) I used the same principles that got me 250 TPS on 2x 3090s. Now I need to buy a DGX Station 🤪.

Youssof Al Toukhi

46,035 views • 29 days ago

Vibe coding at 40,000 feet in the air at 75TPS+ on my MacBook with no WiFi. Qwen 3.6 27B on MTPLX V2 (coming soon!)

Vibe coding at 40,000 feet in the air at 75TPS+ on my MacBook with no WiFi. Qwen 3.6 27B on MTPLX V2 (coming soon!)

Youssof Al Toukhi

61,734 views • 2 months ago

I built a J-Space explorer with several curated sessions. It shows all three regions described in Anthropic's paper on J-Space: sensory, workspace and motor. Model: Qwen 3.6 27B 4-bit

I built a J-Space explorer with several curated sessions. It shows all three regions described in Anthropic's paper on J-Space: sensory, workspace and motor. Model: Qwen 3.6 27B 4-bit

WeZZard

28,148 views • 1 month ago

You can now run Qwen 3.6 27B on <10GB of memory and retain 90% of the intelligence. Today, PrismML dropped Bonsai 27B - which takes their unique compression approach they have already successfully applied to Qwen3.6 8B and Flux2-Klein and applied it to a properly smart model. Here is it using an entire computer for deep research. Long horizon agentic calls already are strong with Qwen3.6 27B and they still are here - just on 10x less memory.

You can now run Qwen 3.6 27B on <10GB of memory and retain 90% of the intelligence. Today, PrismML dropped Bonsai 27B - which takes their unique compression approach they have already successfully applied to Qwen3.6 8B and Flux2-Klein and applied it to a properly smart model. Here is it using an entire computer for deep research. Long horizon agentic calls already are strong with Qwen3.6 27B and they still are here - just on 10x less memory.

Tim Carambat

62,879 views • 1 month ago

I tested Gemma 4 12b on my Macbook Pro M5 Max with 128GB of unified memory. It runs VERY slow for a 12b parameter model. 44 tokens/second. The lava lamp that it produced was also terrible. I would stick to Qwen 3.6 27b or Qwen 3.6 35b. Google is still way behind, even with their local models.

I tested Gemma 4 12b on my Macbook Pro M5 Max with 128GB of unified memory. It runs VERY slow for a 12b parameter model. 44 tokens/second. The lava lamp that it produced was also terrible. I would stick to Qwen 3.6 27b or Qwen 3.6 35b. Google is still way behind, even with their local models.

BridgeMind

70,626 views • 3 months ago

LFM2-Audio just dropped! It's a 1.5B model that understands and generates both text and audio Inference 10x faster + quality on par with models 10x larger Available today on Hugging Face and our playground 🥳

LFM2-Audio just dropped! It's a 1.5B model that understands and generates both text and audio Inference 10x faster + quality on par with models 10x larger Available today on Hugging Face and our playground 🥳

Maxime Labonne

85,053 views • 11 months ago

Qwen3.8-27b produces beautiful results very presentable 😍 Way better than 3.6-27b by a long shot. My three.js and glsl tests are going on, but here is few examples, same prompt with same default settings all run on my 3090. qwen3.6-27b-Q5 vs qwen3.8-27b-Q5

Qwen3.8-27b produces beautiful results very presentable 😍 Way better than 3.6-27b by a long shot. My three.js and glsl tests are going on, but here is few examples, same prompt with same default settings all run on my 3090. qwen3.6-27b-Q5 vs qwen3.8-27b-Q5

AJ

93,007 views • 20 days ago

1/ Offline computer-use models are here. Today, one running on our Mac made it all the way to hotel checkout. We ran Qwen3.8-27B from Qwen through Cua Driver. It also turned a flyer into a Calendar event and reconciled receipts. Every model token stayed on the Mac 🧵

1/ Offline computer-use models are here. Today, one running on our Mac made it all the way to hotel checkout. We ran Qwen3.8-27B from Qwen through Cua Driver. It also turned a flyer into a Calendar event and reconciled receipts. Every model token stayed on the Mac 🧵

Francesco

27,540 views • 20 days ago

Breaking: Browser Use is faster than a human⚡ Running Qwen 3.8 27B on 2x B200s with DFlash2. > speed ✅ > cost ✅ > accuracy ✅ (most of the time) Qwen 27B is better at using the internet than you are. The only bottleneck is website loading. Comment if you want us to deploy this to our cloud 👀

Breaking: Browser Use is faster than a human⚡ Running Qwen 3.8 27B on 2x B200s with DFlash2. > speed ✅ > cost ✅ > accuracy ✅ (most of the time) Qwen 27B is better at using the internet than you are. The only bottleneck is website loading. Comment if you want us to deploy this to our cloud 👀

Browser Use

1,103,961 views • 13 days ago

A nice aspect of our new Gemini 3.6 Flash model is that it is much more token efficient than our 3.5 Flash model. Here's a side-by-side demonstration of that. Nice work by everyone who worked on this model and release!

A nice aspect of our new Gemini 3.6 Flash model is that it is much more token efficient than our 3.5 Flash model. Here's a side-by-side demonstration of that. Nice work by everyone who worked on this model and release!

Jeff Dean

208,839 views • 1 month ago

Today, we’re announcing a $300 million Series C in a mix of primary and secondary funding at a $3.5 billion valuation. We’re excited to bring on @Sequoia as our lead investor in the round, with participation from Spark Capital, Marathon, COATUE, CRV, & a16z.

Today, we’re announcing a $300 million Series C in a mix of primary and secondary funding at a $3.5 billion valuation. We’re excited to bring on @Sequoia as our lead investor in the round, with participation from Spark Capital, Marathon, COATUE, CRV, & a16z.

Mercury

130,445 views • 1 year ago

Qwopus 3.6-27b Coder I had a lot of requests to test it, so I did. I ran the same tests I’ve done on other models. It scored lower on tool-eval-bench than both Qwen 3.6 27b and Qwen 3.6 35b. It also produced broken single-file Tetris and Solar System HTML demos, even after 3 fresh attempts. In the Tetris html, the game stalled when you completed a line. It also randomly changed the pieces when moving them left or right. In the Solar System html, clicking on the sun or any planet broke the rendering — the objects just disappeared. Conclusion: The regular Qwen 3.6 27b and 35b models performed better. What do you think of Qwopus 3.6-27b Coder? Full results & RAW files: Full prompts in the posts below.

Qwopus 3.6-27b Coder I had a lot of requests to test it, so I did. I ran the same tests I’ve done on other models. It scored lower on tool-eval-bench than both Qwen 3.6 27b and Qwen 3.6 35b. It also produced broken single-file Tetris and Solar System HTML demos, even after 3 fresh attempts. In the Tetris html, the game stalled when you completed a line. It also randomly changed the pieces when moving them left or right. In the Solar System html, clicking on the sun or any planet broke the rendering — the objects just disappeared. Conclusion: The regular Qwen 3.6 27b and 35b models performed better. What do you think of Qwopus 3.6-27b Coder? Full results & RAW files: Full prompts in the posts below.

Mia

11,183 views • 2 months ago

We’re bringing powerful AI directly onto robots with Gemini Robotics On-Device. 🤖 It’s our first vision-language-action model to help make robots faster, highly efficient, and adaptable to new tasks and environments - without needing a constant internet connection. 🧵

We’re bringing powerful AI directly onto robots with Gemini Robotics On-Device. 🤖 It’s our first vision-language-action model to help make robots faster, highly efficient, and adaptable to new tasks and environments - without needing a constant internet connection. 🧵

Google DeepMind

819,863 views • 1 year ago

Qwen3-Next (thinking & non-thinking) are now live in BF16 at Hyperbolic! Qwen3-Next is a huge efficiency leap: - 80B MoE with just 3B active params - 10x cheaper to train vs Qwen3-32B - 10x inference throughput for >32K tokens Proud to be a launch partner with Qwen - kudos to this amazing team for keeping pushing open-source AI forward. We’re the first to serve Qwen3-Next on Hugging Face. Give it a try!

Qwen3-Next (thinking & non-thinking) are now live in BF16 at Hyperbolic! Qwen3-Next is a huge efficiency leap: - 80B MoE with just 3B active params - 10x cheaper to train vs Qwen3-32B - 10x inference throughput for >32K tokens Proud to be a launch partner with Qwen - kudos to this amazing team for keeping pushing open-source AI forward. We’re the first to serve Qwen3-Next on Hugging Face. Give it a try!

Yuchen Jin

84,342 views • 11 months ago

Announcing Gemini 3.1 Flash-Lite! ⚡️📷 Our fastest and most cost-efficient Gemini 3 series model yet. A 45 % increase in output speed and it outperforms 2.5 Flash. It also has dynamic thinking levels to match task complexity. Demo:

Announcing Gemini 3.1 Flash-Lite! ⚡️📷 Our fastest and most cost-efficient Gemini 3 series model yet. A 45 % increase in output speed and it outperforms 2.5 Flash. It also has dynamic thinking levels to match task complexity. Demo:

Addy Osmani

53,110 views • 6 months ago

Today we’re announcing our Series B. We’ve raised $200M at a $2B valuation from Greenoaks with participation from Index Ventures, Hanabi, A*, Bain Capital Ventures, CVS Health Ventures, and Definition. Our mission is to simulate all eight billion people on earth, accurately.

Today we’re announcing our Series B. We’ve raised $200M at a $2B valuation from Greenoaks with participation from Index Ventures, Hanabi, A*, Bain Capital Ventures, CVS Health Ventures, and Definition. Our mission is to simulate all eight billion people on earth, accurately.

Simile

659,555 views • 1 month ago

1/4 🚀We are launching Qwen-Image-2.0, a next-generation foundational image generation model. The key highlights of Qwen-Image-2.0 include: Professional Typography Rendering: Supports 1k-token instructions for direct generation of professional infographics, including PPTs, posters, comics, and more. Stronger Semantic Adherence: Native 2K resolution support for finely detailed realistic scenes, including people, nature, and architecture. Improved Text Rendering: Integrated understanding and generation capabilities, unifying image generation and editing in a single mode Lighter Model Architecture: Smaller model size with faster inference speed.

1/4 🚀We are launching Qwen-Image-2.0, a next-generation foundational image generation model. The key highlights of Qwen-Image-2.0 include: Professional Typography Rendering: Supports 1k-token instructions for direct generation of professional infographics, including PPTs, posters, comics, and more. Stronger Semantic Adherence: Native 2K resolution support for finely detailed realistic scenes, including people, nature, and architecture. Improved Text Rendering: Integrated understanding and generation capabilities, unifying image generation and editing in a single mode Lighter Model Architecture: Smaller model size with faster inference speed.

Tongyi Lab

164,097 views • 6 months ago

Under the Tories, our immigration system has been in chaos, with rules not enforced or respected. Today we’re announcing strong and clear steps to boost our border security with a major increase in returns capacity. The Tories wasted time and money on gimmicks, we’re getting a grip.

Under the Tories, our immigration system has been in chaos, with rules not enforced or respected. Today we’re announcing strong and clear steps to boost our border security with a major increase in returns capacity. The Tories wasted time and money on gimmicks, we’re getting a grip.

Seema Malhotra MP

29,165 views • 2 years ago

Announcing GPT-4, a large multimodal model, with our best-ever results on capabilities and alignment:

Announcing GPT-4, a large multimodal model, with our best-ever results on capabilities and alignment:

OpenAI

12,470,565 views • 3 years ago