Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

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

4,545 subscribers

28,148 görüntüleme • 1 ay önce •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Anthropic's new J-Space paper is fascinating. It describes an internal workspace where Claude keeps concepts in mind before they appear in its response. Inspired by the paper, I built a skill that lets Claude (and others) reveal their J-Space. Here's what it looks like.🧵

Anthropic's new J-Space paper is fascinating. It describes an internal workspace where Claude keeps concepts in mind before they appear in its response. Inspired by the paper, I built a skill that lets Claude (and others) reveal their J-Space. Here's what it looks like.🧵

Pietro Schirano

75,701 görüntüleme • 1 ay önce

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 görüntüleme • 3 ay önce

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 görüntüleme • 2 ay önce

Cuebus and Unabandonware preserved a dialer app, featuring Ulala from Space Channel 5! It was preloaded on J-SH07, an early J-SKY keitai from 2001. This was likely intended to show off Mascot Capsule 3D graphics. The right video shows Ulala's model in the PVMicro model viewer.

Cuebus and Unabandonware preserved a dialer app, featuring Ulala from Space Channel 5! It was preloaded on J-SH07, an early J-SKY keitai from 2001. This was likely intended to show off Mascot Capsule 3D graphics. The right video shows Ulala's model in the PVMicro model viewer.

RockmanCosmo

13,902 görüntüleme • 1 yıl önce

Grok 4.5 is INSANE for web dev. I built this scrolling space explorer in just a couple hours with Grok Build. Link below, try it out!

Grok 4.5 is INSANE for web dev. I built this scrolling space explorer in just a couple hours with Grok Build. Link below, try it out!

Anshu

49,427 görüntüleme • 1 ay önce

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 görüntüleme • 21 gün önce

NVIDIA CEO JENSEN HUANG UNVEILED THE RTX 3090 AND THE USED VERSION ON EBAY NOW KILLS A $400/MONTH CLAUDE CODE AND OPENAI BILL the rtx 3090 has 24gb of vram, the same as a new rtx 4090 that costs $2,000. for local ai inference vram matters more than anything else and the 3090 sells for $650-800 used it runs qwen 3.6 27b comfortably, deepseek r1 14b at 60+ tokens per second and mistral 7b for fast automation. 16gb of qwen 3.6 fits with 8gb of headroom for long context alibaba's qwen 3.6 27b beats claude 4.5 opus on realworldqa vision 84.1 vs 77.0 and on ifbench instructions 76.5 vs 58.0. a free open weight model out-benchmarks anthropic's flagship a heavy ai user pays $200 for claude code max, $200 for chatgpt pro, $20 for cursor and $20 for gemini. that's $5,280 a year and a used 3090 pays itself off in 3.5 months install ollama, pull qwen 3.6 27b, point claude code at localhost. same interface, nothing leaves the machine, nothing costs per request bookmark this and read the article below

NVIDIA CEO JENSEN HUANG UNVEILED THE RTX 3090 AND THE USED VERSION ON EBAY NOW KILLS A $400/MONTH CLAUDE CODE AND OPENAI BILL the rtx 3090 has 24gb of vram, the same as a new rtx 4090 that costs $2,000. for local ai inference vram matters more than anything else and the 3090 sells for $650-800 used it runs qwen 3.6 27b comfortably, deepseek r1 14b at 60+ tokens per second and mistral 7b for fast automation. 16gb of qwen 3.6 fits with 8gb of headroom for long context alibaba's qwen 3.6 27b beats claude 4.5 opus on realworldqa vision 84.1 vs 77.0 and on ifbench instructions 76.5 vs 58.0. a free open weight model out-benchmarks anthropic's flagship a heavy ai user pays $200 for claude code max, $200 for chatgpt pro, $20 for cursor and $20 for gemini. that's $5,280 a year and a used 3090 pays itself off in 3.5 months install ollama, pull qwen 3.6 27b, point claude code at localhost. same interface, nothing leaves the machine, nothing costs per request bookmark this and read the article below

starmex

86,410 görüntüleme • 2 ay önce

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 görüntüleme • 1 ay önce

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

11,670 görüntüleme • 27 gün önce

A DEVELOPER ASKED LOCAL AI TO SPIN UP 64 AGENTS IN PARALLEL. IT RAN FOR 8 HOURS WITHOUT ASKING PERMISSION AND WITHOUT A SINGLE API CALL. Gemma 4 refused. Qwen 3.6 said nothing and started working. Zero bills. The model didn't negotiate, it just built.

A DEVELOPER ASKED LOCAL AI TO SPIN UP 64 AGENTS IN PARALLEL. IT RAN FOR 8 HOURS WITHOUT ASKING PERMISSION AND WITHOUT A SINGLE API CALL. Gemma 4 refused. Qwen 3.6 said nothing and started working. Zero bills. The model didn't negotiate, it just built.

0xMarioNawfal

61,845 görüntüleme • 3 ay önce

🇺🇸 LAUREN SANCHEZ: I’M TAKING AN ALL-WOMEN CREW OF EXPLORERS TO SPACE "We’re going on a Blue Origin flight with an incredible group of women—all explorers. Jeff once called me an explorer, and it changed how I saw myself. These women, like Magellan or Cousteau, will see space and return to share how it transforms them." Source: USA Today

🇺🇸 LAUREN SANCHEZ: I’M TAKING AN ALL-WOMEN CREW OF EXPLORERS TO SPACE "We’re going on a Blue Origin flight with an incredible group of women—all explorers. Jeff once called me an explorer, and it changed how I saw myself. These women, like Magellan or Cousteau, will see space and return to share how it transforms them." Source: USA Today

Mario Nawfal

279,129 görüntüleme • 1 yıl önce

🪐 Pinifelipe: "I built a fully-automatic quarry on survival in Space Engineers 2 and I think it is WORTH it!! ➡️ 🪐 Play Now or Wishlist on Steam:

🪐 Pinifelipe: "I built a fully-automatic quarry on survival in Space Engineers 2 and I think it is WORTH it!! ➡️ 🪐 Play Now or Wishlist on Steam:

Space Engineers

45,142 görüntüleme • 29 gün önce

Hey girl , space girl Modern alienne you are Tripped on a needle and found you a motor man Hes got a space suit, a rocket to the space coup Drift it in gear and Out through the stratosphere! Hes gonna change you Try to re create you Hes reptilian - I dont think you understandddddddd

Hey girl , space girl Modern alienne you are Tripped on a needle and found you a motor man Hes got a space suit, a rocket to the space coup Drift it in gear and Out through the stratosphere! Hes gonna change you Try to re create you Hes reptilian - I dont think you understandddddddd

AZEALIA BANKS

46,013 görüntüleme • 3 ay önce

So, Stability AI has this new experimental imageTo3D model, and I just painted a moon buggy in SageBrush, dropped it into their Huggingface space, converted it in Reality Converter, and air dropped it onto the moon – all on #AppleVisionPro 🤯

So, Stability AI has this new experimental imageTo3D model, and I just painted a moon buggy in SageBrush, dropped it into their Huggingface space, converted it in Reality Converter, and air dropped it onto the moon – all on #AppleVisionPro 🤯

Gregory Wieber

63,857 görüntüleme • 2 yıl önce

THIS ENGINEER RUNS CLAUDE CODE WITHOUT PAYING ANTHROPIC A SINGLE DOLLAR RTX 5090 under the desk, Qwen 3.5 35B, 140 tokens per second Claude Code pointed at localhost instead of Anthropic’s servers override two environment variables and your API bill drops to zero he built a full-stack Next.js app from scratch to prove it works then showed every bug and limitation other YouTubers hide same setup I run with two GPUs and Qwen 3.6 27B full breakdown ↓

THIS ENGINEER RUNS CLAUDE CODE WITHOUT PAYING ANTHROPIC A SINGLE DOLLAR RTX 5090 under the desk, Qwen 3.5 35B, 140 tokens per second Claude Code pointed at localhost instead of Anthropic’s servers override two environment variables and your API bill drops to zero he built a full-stack Next.js app from scratch to prove it works then showed every bug and limitation other YouTubers hide same setup I run with two GPUs and Qwen 3.6 27B full breakdown ↓

leopardracer

29,756 görüntüleme • 3 ay önce

MTPLX V2.10 is out! I put a lot of work into this one. Highlights: - Qwen 3.8 Next Support Added: Bare Speed (4 bit) and Optimised Speed (4 bit/8 bit) models added running at 50 - 80 TPS sustained at high contexts. (expect speed improvements in the coming days) - Qwen 3.8 Next mmap: The 32 GB n-gram table streams from SSD via mmap instead of RAM. Both models fit a 96 GB Mac with 0 speed impact. - Qwen 3.8 27B Decode & Prefill boost EVERYWHERE: +15% TPS at 3k context, +29% at 88k, +54% at 147k. Prefill +41%. - 48 GB Macs went from 3 to 4 TPS in swap @ 30k context to 33 TPS. - KV Cache has been solved!: 8 bit and 4 bit cache now barely impacts speed instead of a 50% decline. - Coding agents wall time optimisations: file task dropped from 150s to 44s, and mid-session first token went from ~2s to 0.11s. - CLI UX improvements + 34 bug fixes. My thoughts on Qwen Next? Incredible model. Enormously better at design, and creative tasks with scary good vision. It created what I think is the best flappy bird. maybe even better than the Fable version. It had various difficulties and skins, moving pillars, and upgrades. It also had the most memeified look. Incredibly impressed. However, it is slightly worse than 27B at having code just work straight away. But it's personality is also far better than 27B. Here is the Flappy bird it made below! Made with Qwen Next Optimized Speed one shot@ 57 TPS:

MTPLX V2.10 is out! I put a lot of work into this one. Highlights: - Qwen 3.8 Next Support Added: Bare Speed (4 bit) and Optimised Speed (4 bit/8 bit) models added running at 50 - 80 TPS sustained at high contexts. (expect speed improvements in the coming days) - Qwen 3.8 Next mmap: The 32 GB n-gram table streams from SSD via mmap instead of RAM. Both models fit a 96 GB Mac with 0 speed impact. - Qwen 3.8 27B Decode & Prefill boost EVERYWHERE: +15% TPS at 3k context, +29% at 88k, +54% at 147k. Prefill +41%. - 48 GB Macs went from 3 to 4 TPS in swap @ 30k context to 33 TPS. - KV Cache has been solved!: 8 bit and 4 bit cache now barely impacts speed instead of a 50% decline. - Coding agents wall time optimisations: file task dropped from 150s to 44s, and mid-session first token went from ~2s to 0.11s. - CLI UX improvements + 34 bug fixes. My thoughts on Qwen Next? Incredible model. Enormously better at design, and creative tasks with scary good vision. It created what I think is the best flappy bird. maybe even better than the Fable version. It had various difficulties and skins, moving pillars, and upgrades. It also had the most memeified look. Incredibly impressed. However, it is slightly worse than 27B at having code just work straight away. But it's personality is also far better than 27B. Here is the Flappy bird it made below! Made with Qwen Next Optimized Speed one shot@ 57 TPS:

Youssof Al Toukhi

20,659 görüntüleme • 6 gün önce

$watch a new 27 billion dense parameter model autonomously fail then fix itself on a single rtx 3090. 28 minutes of building, testing, debugging, and serving compressed to under three minutes. qwen 3.6 27b dense, q4_k_m quant, hermes agent as driving harness. one prompt in. mandelbrot fractal explorer with zoom, pan, three palettes, smooth coloring, responsive layout out the other side. 10 verifiable tests, all 10 landed green on its own. what you watch in the video. the model writes mandelbrot.html. writes tests.js. starts the http server. opens the page in its own browser. runs the tests. finds the failures. traces the math. patches the code. reloads. re-runs. iterates again. and again. until every test passes. no human in the loop. local prototyping looks like this in 2026. one consumer card. one open source model. one harness.$

watch a new 27 billion dense parameter model autonomously fail then fix itself on a single rtx 3090. 28 minutes of building, testing, debugging, and serving compressed to under three minutes. qwen 3.6 27b dense, q4_k_m quant, hermes agent as driving harness. one prompt in. mandelbrot fractal explorer with zoom, pan, three palettes, smooth coloring, responsive layout out the other side. 10 verifiable tests, all 10 landed green on its own. what you watch in the video. the model writes mandelbrot.html. writes tests.js. starts the http server. opens the page in its own browser. runs the tests. finds the failures. traces the math. patches the code. reloads. re-runs. iterates again. and again. until every test passes. no human in the loop. local prototyping looks like this in 2026. one consumer card. one open source model. one harness.

Sudo su

46,789 görüntüleme • 4 ay önce

We asked kache about his bespoke IDE setup: “I’ve built a custom framework in Neovim. It’s a server that creates a facade over all the LLMs: Claude, Gemini, OpenAI. They go down all the time, so I always have a model available. If everything breaks, I can still hit DeepSeek.” “Space+I is Gemini 2.5 Pro. Space+K is Gemini Flash. It all renders in a single markdown file. I’ve written commands, three backticks and a command like edit_file, and it just goes.” “It's not open source. People would start posting issues and I’m not interested in fixing them. I’m pulling up the ladder behind me.”

We asked kache about his bespoke IDE setup: “I’ve built a custom framework in Neovim. It’s a server that creates a facade over all the LLMs: Claude, Gemini, OpenAI. They go down all the time, so I always have a model available. If everything breaks, I can still hit DeepSeek.” “Space+I is Gemini 2.5 Pro. Space+K is Gemini Flash. It all renders in a single markdown file. I’ve written commands, three backticks and a command like edit_file, and it just goes.” “It's not open source. People would start posting issues and I’m not interested in fixing them. I’m pulling up the ladder behind me.”

TBPN

361,346 görüntüleme • 1 yıl önce

Yesterday we found out Qwen3.5-27B (dense) beats both the 35B and 122B MoE variants at UI replication from screenshots. Today's question: what about Jackrong's Qwen3.5-27B-Claude-Opus-4.6-Reasoning-Distilled? A distilled 27B with Claude Opus 4.6 reasoning baked in. So I put all 3 in the ring: - Qwen3.5-27B - Qwen3.5-27B-Claude-Opus-Distilled - Claude Opus 4.6 Since the distilled model isn't multimodal, I gave all three the same detailed text prompts describing the UI components from yesterday's test.

Yesterday we found out Qwen3.5-27B (dense) beats both the 35B and 122B MoE variants at UI replication from screenshots. Today's question: what about Jackrong's Qwen3.5-27B-Claude-Opus-4.6-Reasoning-Distilled? A distilled 27B with Claude Opus 4.6 reasoning baked in. So I put all 3 in the ring: - Qwen3.5-27B - Qwen3.5-27B-Claude-Opus-Distilled - Claude Opus 4.6 Since the distilled model isn't multimodal, I gave all three the same detailed text prompts describing the UI components from yesterday's test.

stevibe

126,288 görüntüleme • 5 ay önce