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.

in opencode v0.3.74 we optimized the new qwen models look at it fly

dax

57,283 subscribers

25,841 views • 10 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

The new Qwen 3.5 by Qwen running on-device on iPhone 17 Pro. Qwen 3.5 beats models 4 times its size, has strong visual understanding, and can toggle reasoning on or off. The 2B 6-bit model here is running with MLX optimized for Apple Silicon.

The new Qwen 3.5 by Qwen running on-device on iPhone 17 Pro. Qwen 3.5 beats models 4 times its size, has strong visual understanding, and can toggle reasoning on or off. The 2B 6-bit model here is running with MLX optimized for Apple Silicon.

Adrien Grondin

3,552,168 views • 3 months ago

introducing Qwen Edit. this new models offers incredible image editing capabilities from text prompts. try it now for free!

introducing Qwen Edit. this new models offers incredible image editing capabilities from text prompts. try it now for free!

Krea

76,657 views • 9 months ago

Alibaba’s Qwen 3.5 is now running fully on-device on the iPhone 17 Pro. It outperforms models 4x its size, delivers strong visual understanding, and lets you switch reasoning on or off. This demo uses the 2B 6-bit version, optimized with MLX for Apple Silicon.

Alibaba’s Qwen 3.5 is now running fully on-device on the iPhone 17 Pro. It outperforms models 4x its size, delivers strong visual understanding, and lets you switch reasoning on or off. This demo uses the 2B 6-bit version, optimized with MLX for Apple Silicon.

Hugging Models

202,648 views • 2 months ago

We built Openwork! This time with OpenCode + Composio This agent can now: - use opencode zen models like Big Pickle, GLM 4.7, MiniMax - access local files and your terminal via opencode - chain actions across local files and cloud apps in one flow completely free and open source:

We built Openwork! This time with OpenCode + Composio This agent can now: - use opencode zen models like Big Pickle, GLM 4.7, MiniMax - access local files and your terminal via opencode - chain actions across local files and cloud apps in one flow completely free and open source:

Karan Vaidya

62,689 views • 4 months ago

The latest Qwen 3 VL by Qwen running on iPhone 17 Pro with MLX Qwen 3 VL brings upgraded visual understanding, recognition, and OCR capabilities without sacrificing text performance like previous models The 4B model here is close to Qwen 2.5 VL 72B in many benchmarks

The latest Qwen 3 VL by Qwen running on iPhone 17 Pro with MLX Qwen 3 VL brings upgraded visual understanding, recognition, and OCR capabilities without sacrificing text performance like previous models The 4B model here is close to Qwen 2.5 VL 72B in many benchmarks

Adrien Grondin

109,700 views • 7 months ago

They did use 3D models and we can fly through the scenes and check it all out! #threejs Shopify Using the Needle three.js inspector

They did use 3D models and we can fly through the scenes and check it all out! #threejs Shopify Using the Needle three.js inspector

🌵 Marcel Wiessler

157,208 views • 6 months ago

This new VRChat update is flawless!!! Look at how well optimized all these distant networked synced objects are! Wow! Thanks, Tupper!

This new VRChat update is flawless!!! Look at how well optimized all these distant networked synced objects are! Wow! Thanks, Tupper!

Mawntee

24,230 views • 1 year ago

Today we got a new look at the iPhone Fold dummy models and the iPhone 18 Pro/Pro Max models. The iPhone Fold is still on track for release in the Fall later this year. Will you be getting an iPhone Fold? #appleleaks #applenews #iphonefold #iphone18 #foldablephone

Today we got a new look at the iPhone Fold dummy models and the iPhone 18 Pro/Pro Max models. The iPhone Fold is still on track for release in the Fall later this year. Will you be getting an iPhone Fold? #appleleaks #applenews #iphonefold #iphone18 #foldablephone

Jon Rettinger

127,184 views • 2 months ago

Introducing Qwen 3 + Deep Research! We built a deep research agent with Qwen 3 and it performed better than most open source models that we've tried. the code is completely open source and free! built with 's Langgraph Together AI and uses Perplexity Tavily for search here's the code link:

Introducing Qwen 3 + Deep Research! We built a deep research agent with Qwen 3 and it performed better than most open source models that we've tried. the code is completely open source and free! built with 's Langgraph Together AI and uses Perplexity Tavily for search here's the code link:

Soham

34,566 views • 1 year ago

The future is now..... "in just a few minutes, my agent simulated, it customized, it optimized, it automated a response to the disruption." Molly is the Head of Dynamic Scheduling & Optimization at Palantir......doing this in every vertical we are in.

The future is now..... "in just a few minutes, my agent simulated, it customized, it optimized, it automated a response to the disruption." Molly is the Head of Dynamic Scheduling & Optimization at Palantir......doing this in every vertical we are in.

Chad Wahlquist

13,303 views • 11 months ago

When we say Ducks fly together, we MEAN IT! Steppin' up the experience at @hondacenter 🦆 🎟️:

When we say Ducks fly together, we MEAN IT! Steppin' up the experience at @hondacenter 🦆 🎟️:

Anaheim Ducks

117,291 views • 1 year ago

Mullin: 1 in 10,000 kids, when we first started tracking autism, was diagnosed as autistic. Today it's 1 in 10. Why wouldn’t we look at it? Kasie: We have looked at it Mullin: So, we shouldn’t look at it again? Kasie: The study showed there was no connection

Mullin: 1 in 10,000 kids, when we first started tracking autism, was diagnosed as autistic. Today it's 1 in 10. Why wouldn’t we look at it? Kasie: We have looked at it Mullin: So, we shouldn’t look at it again? Kasie: The study showed there was no connection

Acyn

663,690 views • 9 months ago

The fact that we're here shows that we care and we want to win. FLY, TL, & FLY again - all in the new episode of On Cloud9 Kia.

The fact that we're here shows that we care and we want to win. FLY, TL, & FLY again - all in the new episode of On Cloud9 Kia.

Cloud9 Kia

66,638 views • 1 year ago

Running mlx optimized models is easy 🙂

Running mlx optimized models is easy 🙂

Andrew I. Christianson

32,974 views • 10 months ago

it's time I got a new job, it's my first day at OpenCode

it's time I got a new job, it's my first day at OpenCode

James Long

163,162 views • 3 months ago

Today's autoregressive models generate one token at a time. Mercury 2 generates tokens in parallel. Over 1,000 tok/sec on standard GPUs, at comparable quality to speed-optimized models. Since launch, the community has been showing what diffusion LLMs can unlock. Thanks to the team at Clyep for the breakdown.

Today's autoregressive models generate one token at a time. Mercury 2 generates tokens in parallel. Over 1,000 tok/sec on standard GPUs, at comparable quality to speed-optimized models. Since launch, the community has been showing what diffusion LLMs can unlock. Thanks to the team at Clyep for the breakdown.

Inception

21,104 views • 28 days ago

First store. First launch. First look at the future. Alibaba Group brings its Qwen AI Glasses global debut to Nanjing Lukou International Airport, spotlighting the city’s growing role in AI and smart manufacturing. Where innovation meets runway traffic. Watch this space. Qwen Alibaba Group

First store. First launch. First look at the future. Alibaba Group brings its Qwen AI Glasses global debut to Nanjing Lukou International Airport, spotlighting the city’s growing role in AI and smart manufacturing. Where innovation meets runway traffic. Watch this space. Qwen Alibaba Group

Discover Nanjing

1,238,853 views • 1 month ago

The most honest response about AGI I talked to Olive Song, senior researcher at MiniMax (official), at 9 pm on a Sunday in Beijing. She was waiting on results from the new M2.2 model experiments. We talked RL models that try to hack rewards, why alignment fails in practice, why tiny engineering details matter more than new algorithms, and what open models actually look like in production. AGI came up only at the end. For a reason. Full conversation in the comments.

The most honest response about AGI I talked to Olive Song, senior researcher at MiniMax (official), at 9 pm on a Sunday in Beijing. She was waiting on results from the new M2.2 model experiments. We talked RL models that try to hack rewards, why alignment fails in practice, why tiny engineering details matter more than new algorithms, and what open models actually look like in production. AGI came up only at the end. For a reason. Full conversation in the comments.

Ksenia_TuringPost

40,069 views • 4 months ago

Small models are so powerful! Alibaba Qwen released QwQ-32B, a reasoning model that beats DeepSeek-R1 (671B) and OpenAI o1-mini! We at Hyperbolic Labs now serve QwQ 32B in bf16! As an inference provider of Hugging Face, you can chat with it directly on the model's Hugging Face page!

Small models are so powerful! Alibaba Qwen released QwQ-32B, a reasoning model that beats DeepSeek-R1 (671B) and OpenAI o1-mini! We at Hyperbolic Labs now serve QwQ 32B in bf16! As an inference provider of Hugging Face, you can chat with it directly on the model's Hugging Face page!

Yuchen Jin

65,950 views • 1 year ago

OpenCode, now on your desktop (in beta)

OpenCode, now on your desktop (in beta)

OpenCode

236,003 views • 5 months ago