正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

A 27B open-weight model built this entire 3D Mars colony from one prompt. Qwen3.8-27B handled the scene, structures, terrain, lighting and interactive elements without an agentic loop. Really impressive progress for models this size.

Noctus

1,175 subscribers

13,602 次观看 • 8 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Every big MoE model I test on my 3090 is basically to see how good it is compared to Qwen3.6-27B. "How good is it compared to Qwen3.6-27B?" is the question I get asked the most, and that shows how much people love and, more importantly, trust the 27B 27B is battle tested. It has proven its worth and has nothing left to prove. Now it just needs to make way for the next 27B. Here’s an example video: a Three.js task, same prompt, not oneshot but two shots for all models. All ran on my 3090 + 64GB VRAM Qwen-3.6-27b fully on vram while others have experts offloaded to system ram. Pinned on the left: Qwen3.6-27B-Q5 On the right, i'm switching between Inkling-Small-Q4_K_M DSV4-Flash-0731-UD-IQ1 Ling-3.0-Flash-Q4_K_M Qwen3.6-27B nailed it. The effects and visuals are just spot on.The other models got some things right, but not everything. Second place would have to go to Inkling-Small while DSV4-Flash-0731 and Ling-3.0-Flash failed to capture the full requirements. This is also why we’re all excited for Qwen Qwen3.8-27B!

Every big MoE model I test on my 3090 is basically to see how good it is compared to Qwen3.6-27B. "How good is it compared to Qwen3.6-27B?" is the question I get asked the most, and that shows how much people love and, more importantly, trust the 27B 27B is battle tested. It has proven its worth and has nothing left to prove. Now it just needs to make way for the next 27B. Here’s an example video: a Three.js task, same prompt, not oneshot but two shots for all models. All ran on my 3090 + 64GB VRAM Qwen-3.6-27b fully on vram while others have experts offloaded to system ram. Pinned on the left: Qwen3.6-27B-Q5 On the right, i'm switching between Inkling-Small-Q4_K_M DSV4-Flash-0731-UD-IQ1 Ling-3.0-Flash-Q4_K_M Qwen3.6-27B nailed it. The effects and visuals are just spot on.The other models got some things right, but not everything. Second place would have to go to Inkling-Small while DSV4-Flash-0731 and Ling-3.0-Flash failed to capture the full requirements. This is also why we’re all excited for Qwen Qwen3.8-27B!

AJ

10,669 次观看 • 15 天前

It's official: Qwen3.8-27B just scored 52 on the Artificial Analysis Intelligence Index. We now have an open-weight model that matches GPT-5.6 Luna (max) AND can run locally... even in your browser with custom WebGPU kernels! What a time to be alive! 🤯

It's official: Qwen3.8-27B just scored 52 on the Artificial Analysis Intelligence Index. We now have an open-weight model that matches GPT-5.6 Luna (max) AND can run locally... even in your browser with custom WebGPU kernels! What a time to be alive! 🤯

Xenova

167,603 次观看 • 6 天前

Kimi K3 just generated a Red Dead Redemption 2-style open-world game... 🤯 A few months ago this would've sounded impossible. Now open-weight models are building explorable worlds with terrain, gameplay systems, and impressive visual fidelity from a single prompt.

Kimi K3 just generated a Red Dead Redemption 2-style open-world game... 🤯 A few months ago this would've sounded impossible. Now open-weight models are building explorable worlds with terrain, gameplay systems, and impressive visual fidelity from a single prompt.

WorldofAI

94,901 次观看 • 1 个月前

I plugged ChatGPT Luna 5.6 and Claude Opus 5 into Blender through MCP, and one of them is one-shotting entire 3D scenes now. Top is Luna 5.6 in fast mode modeling ship cannons with a firing animation. Watching the scene grow mesh by mesh in real time is a separate kind of dopamine. Bottom is Opus 5 building a full carriage scene with terrain, rocks and lighting. This one is simply built for 3D -- the whole thing from a single prompt with zero retries and zero corrections. The entire bridge is one open-source repo, no Python and no modeling skills required: > The repo is with 16.9k stars under MIT license. > It works with any model -- Claude, GPT, Cursor, any MCP client. > The model sees your scene through a live socket and edits it in real time. A year ago this workflow didn't exist, and now the gap between an idea and a rendered 3D scene is one prompt. Save this one -- you will come back for the repo ↓

I plugged ChatGPT Luna 5.6 and Claude Opus 5 into Blender through MCP, and one of them is one-shotting entire 3D scenes now. Top is Luna 5.6 in fast mode modeling ship cannons with a firing animation. Watching the scene grow mesh by mesh in real time is a separate kind of dopamine. Bottom is Opus 5 building a full carriage scene with terrain, rocks and lighting. This one is simply built for 3D -- the whole thing from a single prompt with zero retries and zero corrections. The entire bridge is one open-source repo, no Python and no modeling skills required: > The repo is with 16.9k stars under MIT license. > It works with any model -- Claude, GPT, Cursor, any MCP client. > The model sees your scene through a live socket and edits it in real time. A year ago this workflow didn't exist, and now the gap between an idea and a rendered 3D scene is one prompt. Save this one -- you will come back for the repo ↓

slash1s

150,102 次观看 • 28 天前

I can't believe this is open source. Wan 2.1 has great prompt coherence and the realism is really impressive for an open source model. This is image to video by the way.

I can't believe this is open source. Wan 2.1 has great prompt coherence and the realism is really impressive for an open source model. This is image to video by the way.

Halim Alrasihi

65,185 次观看 • 1 年前

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 次观看 • 1 个月前

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

27,295 次观看 • 9 天前

Qwen3.8 just dropped. I gave it one of my favorite frontend tests: One prompt + one reference image. The task: rebuild a 3D globe dashboard. 🌎 It built a working page. Layout, structure, all there. Texture looked decent. Lighting flat. Glass panels had no depth. Some elements didn't match the reference. On frontend, not close to top-tier models like Kimi K3.

Qwen3.8 just dropped. I gave it one of my favorite frontend tests: One prompt + one reference image. The task: rebuild a 3D globe dashboard. 🌎 It built a working page. Layout, structure, all there. Texture looked decent. Lighting flat. Glass panels had no depth. Some elements didn't match the reference. On frontend, not close to top-tier models like Kimi K3.

Kai

29,292 次观看 • 1 个月前

You can build your 3D models directly from a prompt into Claude code. All thanks to this beautiful python project, build123 a parametric modeling framework for 2D and 3D CAD. It is built on the Open Cascade geometric kernel and it is suitable for 3D printing.

You can build your 3D models directly from a prompt into Claude code. All thanks to this beautiful python project, build123 a parametric modeling framework for 2D and 3D CAD. It is built on the Open Cascade geometric kernel and it is suitable for 3D printing.

Marco Franzon

20,819 次观看 • 4 个月前

📢WorldAgents: 3D worlds only from 2D image models - without any training! We propose an agentic approach with a Director (VLM) to plan the scene, a Generator (Flux or NanoBanana) for new views, and a Verifier (VLM) for selection / 3D consistency. -> High-fidelity 3D worlds from a single text prompt. What's remarkable: our agents find consistent views from 2D image models to obtain 3D-consistent worlds; this shows that image models contain world priors - agents just need to find them! Great work by Ziya Erkoç Angela Dai

📢WorldAgents: 3D worlds only from 2D image models - without any training! We propose an agentic approach with a Director (VLM) to plan the scene, a Generator (Flux or NanoBanana) for new views, and a Verifier (VLM) for selection / 3D consistency. -> High-fidelity 3D worlds from a single text prompt. What's remarkable: our agents find consistent views from 2D image models to obtain 3D-consistent worlds; this shows that image models contain world priors - agents just need to find them! Great work by Ziya Erkoç Angela Dai

Matthias Niessner

19,020 次观看 • 5 个月前

Kimi K3 is insane🤯 It built an Animal Crossing-style game, and it generated a fully playable experience with the cozy aesthetic, interactions, and gameplay loop in a single shot. Open-weight models are starting to rival the best closed models for game generation. The pace of progress is getting ridiculous. 🌱🎮

Kimi K3 is insane🤯 It built an Animal Crossing-style game, and it generated a fully playable experience with the cozy aesthetic, interactions, and gameplay loop in a single shot. Open-weight models are starting to rival the best closed models for game generation. The pace of progress is getting ridiculous. 🌱🎮

WorldofAI

449,456 次观看 • 1 个月前

Here's a comparison i never thought i would make Qwen-3.8-27b vs Gemini-3.7-flash Yes, you read it right! I don't know what to say, this is soo damn impressive. the difference is hugeee🤯 Take a look at this result 😍 (watch it in highest quality) Same prompt, both one shot on web-chat ui Qwen-3.8-27b produces consistent beautiful, visually stunning results. This is one of the best water surface simulations i have seen across every local models i have run and at the same time beating Gemini-3.7-flash result. And this is running on my 3090. And yes its Q5, not even f8.

Here's a comparison i never thought i would make Qwen-3.8-27b vs Gemini-3.7-flash Yes, you read it right! I don't know what to say, this is soo damn impressive. the difference is hugeee🤯 Take a look at this result 😍 (watch it in highest quality) Same prompt, both one shot on web-chat ui Qwen-3.8-27b produces consistent beautiful, visually stunning results. This is one of the best water surface simulations i have seen across every local models i have run and at the same time beating Gemini-3.7-flash result. And this is running on my 3090. And yes its Q5, not even f8.

AJ

248,036 次观看 • 9 天前

watch anon! 27 billion parameter model dancing at 42 tokens a second on a used rtx 3060ti, that costs 200 dollars. consuming 159 watts. temp 62 degrees. pushing almost 100% on the gpu. 6.8 of 8 gigs used with a 128k context window loaded. and every one of those spikes is the model reasoning and firing tool calls. the model is bonsai 27b at 1 bit. PrismML took qwen 3.6 27b, and crushed it to 3.9 gigabytes, about a single sign bit per weight. it drops onto an 8gb rtx 3060 ti, an ampere card from 2020, and it doesn't just load, it serves, it holds the full 128k window, it runs a hermes agent for half an hour straight, it hits its own failures and recovers, it never once drops the loop. the absurd part is the power meter. that same 27b, in its normal quant 4, wants a 24gb card and nearly 17 gigs of weights. this is it at 3.9, doing agentic work at 160 watts, on the tier people call budget. the numbers are sitting right there on nvtop, not in a slide, not a claim, the meter reading while it works. so i keep landing on one question. the model is open, apache 2.0. the card is old and cheap. the whole thing runs offline. why is almost nobody actually running this. is it the hardware, the setup, or did nobody tell you a 27b fits on the card already in your closet.

watch anon! 27 billion parameter model dancing at 42 tokens a second on a used rtx 3060ti, that costs 200 dollars. consuming 159 watts. temp 62 degrees. pushing almost 100% on the gpu. 6.8 of 8 gigs used with a 128k context window loaded. and every one of those spikes is the model reasoning and firing tool calls. the model is bonsai 27b at 1 bit. PrismML took qwen 3.6 27b, and crushed it to 3.9 gigabytes, about a single sign bit per weight. it drops onto an 8gb rtx 3060 ti, an ampere card from 2020, and it doesn't just load, it serves, it holds the full 128k window, it runs a hermes agent for half an hour straight, it hits its own failures and recovers, it never once drops the loop. the absurd part is the power meter. that same 27b, in its normal quant 4, wants a 24gb card and nearly 17 gigs of weights. this is it at 3.9, doing agentic work at 160 watts, on the tier people call budget. the numbers are sitting right there on nvtop, not in a slide, not a claim, the meter reading while it works. so i keep landing on one question. the model is open, apache 2.0. the card is old and cheap. the whole thing runs offline. why is almost nobody actually running this. is it the hardware, the setup, or did nobody tell you a 27b fits on the card already in your closet.

Sudo su

23,225 次观看 • 28 天前

gemini 3 one shotted this. a fully interactive 3d globe that lets you explore and stream radio stations from around the world. this model is incredible.

gemini 3 one shotted this. a fully interactive 3d globe that lets you explore and stream radio stations from around the world. this model is incredible.

Sahil

170,390 次观看 • 9 个月前

Alright guys, wow. Qwen 3.8 27B is basically Qwen 4. What we have here is one of the best one-shot shark survival games I've made with any model. I ran this same prompt through fable, and the biggest thing all models struggle with in this test is the top-down view of the sharks. Fable even had all of the fins reversed and details jumbled on the first turn. Before now, it was really a 2 to 8 turn test to get something final regardless of model. Qwen 3.8 27B just nailed this in one output, no harness at all, just purely the model thoroughly thinking before outputting the final result. On every asset used, different shark variants, everything, it all looks incredibly tight. The boat movement, shark speed and engagement, everything is so much better than I expected, and I was expecting a lot. Imagine what 8 turns would do in a harness? This confirms to me that while Qwen 3.8 27B thinks a lot, for the first time in a local model on the base weights, IT MIGHT ACTUALLY BE WORTH IT This is a Frontier Lab model result, and it ran on my 5090 at 60tps in Q5_K_M. I am just in complete astoundment at what Qwen has accomplished here, and I am incredibly grateful that this model is open source. The speed will also increase drastically with optimisations. This is just an incredible day. What a blessing. More to come!

Alright guys, wow. Qwen 3.8 27B is basically Qwen 4. What we have here is one of the best one-shot shark survival games I've made with any model. I ran this same prompt through fable, and the biggest thing all models struggle with in this test is the top-down view of the sharks. Fable even had all of the fins reversed and details jumbled on the first turn. Before now, it was really a 2 to 8 turn test to get something final regardless of model. Qwen 3.8 27B just nailed this in one output, no harness at all, just purely the model thoroughly thinking before outputting the final result. On every asset used, different shark variants, everything, it all looks incredibly tight. The boat movement, shark speed and engagement, everything is so much better than I expected, and I was expecting a lot. Imagine what 8 turns would do in a harness? This confirms to me that while Qwen 3.8 27B thinks a lot, for the first time in a local model on the base weights, IT MIGHT ACTUALLY BE WORTH IT This is a Frontier Lab model result, and it ran on my 5090 at 60tps in Q5_K_M. I am just in complete astoundment at what Qwen has accomplished here, and I am incredibly grateful that this model is open source. The speed will also increase drastically with optimisations. This is just an incredible day. What a blessing. More to come!

Kyle Hessling

24,917 次观看 • 9 天前

A 27B parameter model used to need a server room. Now it runs on: • iPhone • Android • Mac PrismML's Bonsai makes it possible. • 1-bit weights • 27B params in just 3.9GB • ~90% of full precision quality (PrismML evals) • Better than the 2-bit version at less than half the size The entire Bonsai family is now live in RunAnywhere. • 1.7B to 27B models • 1-bit + 2-bit ternary • Thinking mode On iOS and Mac, Bonsai runs through ggml's llama.cpp and Apple's MLX. On Android, Bonsai runs through ggml's llama.cpp and directly on the Qualcomm Hexagon NPU through QHexRT, our proprietary inference runtime. We built custom silicon kernels to make 1-bit inference on an NPU possible for the first time. Two years ago this needed a data center. Now it thinks in airplane mode. Now available in the RunAnywhere app on the App Store and Google Play.

A 27B parameter model used to need a server room. Now it runs on: • iPhone • Android • Mac PrismML's Bonsai makes it possible. • 1-bit weights • 27B params in just 3.9GB • ~90% of full precision quality (PrismML evals) • Better than the 2-bit version at less than half the size The entire Bonsai family is now live in RunAnywhere. • 1.7B to 27B models • 1-bit + 2-bit ternary • Thinking mode On iOS and Mac, Bonsai runs through ggml's llama.cpp and Apple's MLX. On Android, Bonsai runs through ggml's llama.cpp and directly on the Qualcomm Hexagon NPU through QHexRT, our proprietary inference runtime. We built custom silicon kernels to make 1-bit inference on an NPU possible for the first time. Two years ago this needed a data center. Now it thinks in airplane mode. Now available in the RunAnywhere app on the App Store and Google Play.

RunAnywhere (YC W26)

16,421 次观看 • 1 个月前

Welcome to the 3D Layer of the Internet We are thrilled to share our latest features Prompt-to-3D engine and Scene Studio Your text based prompts and photos can now be transformed from simple concepts into fully-rendered, interactive 3D models. It parses complex topology, handles multi-view reconstruction, and even lets you restyle your model instantly with single-click filters like low-poly, voxel, and Voronoi shells. Within the all-new Scene Studio, you can construct immersive 3D environments that reflect your exact style. Position your assets in a full sandbox space, adjust advanced lighting and environment colors, and add the finishing touches with custom camera angles, fog settings, and real-time script parameters. This is the future of the open web. This is

Welcome to the 3D Layer of the Internet We are thrilled to share our latest features Prompt-to-3D engine and Scene Studio Your text based prompts and photos can now be transformed from simple concepts into fully-rendered, interactive 3D models. It parses complex topology, handles multi-view reconstruction, and even lets you restyle your model instantly with single-click filters like low-poly, voxel, and Voronoi shells. Within the all-new Scene Studio, you can construct immersive 3D environments that reflect your exact style. Position your assets in a full sandbox space, adjust advanced lighting and environment colors, and add the finishing touches with custom camera angles, fog settings, and real-time script parameters. This is the future of the open web. This is

three.ws

37,443 次观看 • 2 个月前

Local models just got a free intelligence upgrade. Someone took the new Qwen3.8-27B (the one that already runs in 22GB) and only changed the chat template. No fine-tune. No new training. Just a smarter system prompt that kills all the filler and forces the model to stay sharp. Result: the same weights are now fixing real post-cutoff bugs faster and cleaner than Claude Opus 5 High in their tests. They call it the Sharp template. It’s free. Drop it on any Qwen3.5 / 3.6 / 3.8 model and it just works with llama.cpp. This is the kind of quiet upgrade that actually moves the needle for people running models locally.

Local models just got a free intelligence upgrade. Someone took the new Qwen3.8-27B (the one that already runs in 22GB) and only changed the chat template. No fine-tune. No new training. Just a smarter system prompt that kills all the filler and forces the model to stay sharp. Result: the same weights are now fixing real post-cutoff bugs faster and cleaner than Claude Opus 5 High in their tests. They call it the Sharp template. It’s free. Drop it on any Qwen3.5 / 3.6 / 3.8 model and it just works with llama.cpp. This is the kind of quiet upgrade that actually moves the needle for people running models locally.

Harman

72,520 次观看 • 4 天前

Seedance 2.5 is now LIVE on OpenGradient! This entire film was generated from a single prompt. One take, no edits. → Up to 30-second clips from one prompt → 10,000 character prompts for full scene-by-scene direction → Up to 30 reference uploads for character and environment consistency → Native audio and sound design built in Even the judges agree: it's a 2.5. Try it now →

Seedance 2.5 is now LIVE on OpenGradient! This entire film was generated from a single prompt. One take, no edits. → Up to 30-second clips from one prompt → 10,000 character prompts for full scene-by-scene direction → Up to 30 reference uploads for character and environment consistency → Native audio and sound design built in Even the judges agree: it's a 2.5. Try it now →

OpenGradient (∇, ∇)

11,705 次观看 • 16 天前

Inferact CEO Simon Mo says open and closed models are converging. The moat is environment: "What really differentiates open-weight models from closed-weight models? In the end, there's not much differentiation. It's more about the distribution strategy and go-to-market strategy. Capability-wise, I don't really see a big gap, not even today." "One of the most important parts is just the data. It's about who gets what data, and then what are the environments you are building to let the model improve on itself." "For Moonshot, they have built some of the best environments for front-end coding... the ability for this model to code and then see what the rendered code is, and then continue looping in this iterative process." "Now, this is about their environment to improve the model. It's not about just source data. It's not about where they get the data from. Rather, it's who can build the best environment and who can make the most optimization and algorithmic choices to leverage all this learning from this environment." "The next year is all gonna be about that: how open-weight model labs are differentiating and really getting the model to meet the real world." Simon Mo

Inferact CEO Simon Mo says open and closed models are converging. The moat is environment: "What really differentiates open-weight models from closed-weight models? In the end, there's not much differentiation. It's more about the distribution strategy and go-to-market strategy. Capability-wise, I don't really see a big gap, not even today." "One of the most important parts is just the data. It's about who gets what data, and then what are the environments you are building to let the model improve on itself." "For Moonshot, they have built some of the best environments for front-end coding... the ability for this model to code and then see what the rendered code is, and then continue looping in this iterative process." "Now, this is about their environment to improve the model. It's not about just source data. It's not about where they get the data from. Rather, it's who can build the best environment and who can make the most optimization and algorithmic choices to leverage all this learning from this environment." "The next year is all gonna be about that: how open-weight model labs are differentiating and really getting the model to meet the real world." Simon Mo

a16z

39,353 次观看 • 12 天前