atomic.chat's banner

atomic.chat

@atomic_chat_hq • 18,906 subscribers

The simplest way to run open models on any hardware. Powered by TurboQuant. Team: @gladkos @skinbagwbones @AlexFromAtomic @danyurkin @quantizedden

Shorts

DeepSeek V4.1 Flash vs Luna at Tesla Roadster 🏎️ DeepSeek V4.1 Flash 1017 re-created the Tesla Roadster event in 3D voxels for $0.89 while GPT-6 Luna's version cost $1.07 Run DeepSeek Flash locally or via API ->

DeepSeek V4.1 Flash vs Luna at Tesla Roadster 🏎️ DeepSeek V4.1 Flash 1017 re-created the Tesla Roadster event in 3D voxels for $0.89 while GPT-6 Luna's version cost $1.07 Run DeepSeek Flash locally or via API ->

181,042 просмотров

Run Ternary Bonsai 2 locally in Atomic Chat 🪴 PrismML shrank Qwen3.5 7x so the 9B goes from 17.9 GB to just 2.42 GB and it keeps up or outperforms the original model on benchmarks Run AI models locally ->

Run Ternary Bonsai 2 locally in Atomic Chat 🪴 PrismML shrank Qwen3.5 7x so the 9B goes from 17.9 GB to just 2.42 GB and it keeps up or outperforms the original model on benchmarks Run AI models locally ->

76,489 просмотров

Fable 5 totally crushed our new contest, but it cost 6x more than Opus 4.8! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics demos Prompts: — A train derailing off a broken bridge into the water — Two cars jumping off ramps and colliding mid-air over a canyon — A monster truck crushing a row of parked cars Outputs: Fable 5: 62,158 tokens, $3.12 GPT 5.5: 37,753 tokens, $1.14 Opus 4.8: 22,280 tokens, $0.56 GLM 5.2: 36,246 tokens, $0.08 Fable 5 did all three scenes at A+. The crashes looked real, things fell and broke the right way, and nothing went through the ground or floated. GPT 5.5 was the closest to Fable. In the Bigfoot show, we think GPT was even a little better. GLM 5.2 did not win any scene, but it was the cheapest by far. Fable is the best pick for quality, but you pay more for it.

Fable 5 totally crushed our new contest, but it cost 6x more than Opus 4.8! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics demos Prompts: — A train derailing off a broken bridge into the water — Two cars jumping off ramps and colliding mid-air over a canyon — A monster truck crushing a row of parked cars Outputs: Fable 5: 62,158 tokens, $3.12 GPT 5.5: 37,753 tokens, $1.14 Opus 4.8: 22,280 tokens, $0.56 GLM 5.2: 36,246 tokens, $0.08 Fable 5 did all three scenes at A+. The crashes looked real, things fell and broke the right way, and nothing went through the ground or floated. GPT 5.5 was the closest to Fable. In the Bigfoot show, we think GPT was even a little better. GLM 5.2 did not win any scene, but it was the cheapest by far. Fable is the best pick for quality, but you pay more for it.

2,843,193 просмотров

Run Bonsai 27B locally on a 16 GB Mac 🥷 Bonsai 2 27B is PrismML's ternary build of Qwen3.8 27B that keeps 98.2% of FP16 quality in 7 GB, it made a voxel Japanese pagoda in one prompt with Three.js! Run AI models locally -

Run Bonsai 27B locally on a 16 GB Mac 🥷 Bonsai 2 27B is PrismML's ternary build of Qwen3.8 27B that keeps 98.2% of FP16 quality in 7 GB, it made a voxel Japanese pagoda in one prompt with Three.js! Run AI models locally -

338,704 просмотров

New Claude Sonnet 5 performs at GPT 5.5 level 6x cheaper! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics crash demos Prompts: - A car crashes into a brick wall - A wrecking ball destroys a house - A catapult throws a rock at a castle wall Outputs: Sonnet 5: 15,047 tokens, $0.15 Opus 4.8: 23,063 tokens, $0.58 Sonnet 4.6: 25,824 tokens, $0.39 GPT 5.5: 31,152 tokens, $0.94 Sonnet 5 did as well as Opus 4.8 and GPT 5.5 on all three tests. In the wrecking ball test, it beat Opus 4.8. The cable moves smoothly and every hit connects. In the catapult test, it beat GPT 5.5. The rock always lands inside the wall. Sonnet 5 still needs better detail and graphics. But it used fewer tokens than every other model

New Claude Sonnet 5 performs at GPT 5.5 level 6x cheaper! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics crash demos Prompts: - A car crashes into a brick wall - A wrecking ball destroys a house - A catapult throws a rock at a castle wall Outputs: Sonnet 5: 15,047 tokens, $0.15 Opus 4.8: 23,063 tokens, $0.58 Sonnet 4.6: 25,824 tokens, $0.39 GPT 5.5: 31,152 tokens, $0.94 Sonnet 5 did as well as Opus 4.8 and GPT 5.5 on all three tests. In the wrecking ball test, it beat Opus 4.8. The cable moves smoothly and every hit connects. In the catapult test, it beat GPT 5.5. The rock always lands inside the wall. Sonnet 5 still needs better detail and graphics. But it used fewer tokens than every other model

730,766 просмотров

Sakana Fugu surprisingly performed near GLM 5.2 level but 17× more expensive! We gave the same prompt to 4 models: build a complete live Trader Desk with both frontend and backend components, real-time market data fetched from external APIs for 8 symbols, and a custom dark-theme UI. Outputs: Fugu Ultra — 22,225 t, $0.51 Opus 4.8 — 15,802 t, $0.31 GPT-5.5 — 11,474 t, $0.26 GLM 5.2 — 13,677 t, $0.03 Fugu created the most polished and feature-rich trading desk in the run. GLM 5.2 was very close behind, with a similarly complete multi-panel interface and live data, but at a much lower cost. Opus and GPT also performed well, delivering solid results with a better balance between quality and cost

Sakana Fugu surprisingly performed near GLM 5.2 level but 17× more expensive! We gave the same prompt to 4 models: build a complete live Trader Desk with both frontend and backend components, real-time market data fetched from external APIs for 8 symbols, and a custom dark-theme UI. Outputs: Fugu Ultra — 22,225 t, $0.51 Opus 4.8 — 15,802 t, $0.31 GPT-5.5 — 11,474 t, $0.26 GLM 5.2 — 13,677 t, $0.03 Fugu created the most polished and feature-rich trading desk in the run. GLM 5.2 was very close behind, with a similarly complete multi-panel interface and live data, but at a much lower cost. Opus and GPT also performed well, delivering solid results with a better balance between quality and cost

745,454 просмотров

Qwen 3.7-max beats Opus 4.7 and GPT-5.5 We tested three frontier models on a real agentic task: write a Tetris bot that plays the game and trains itself. Each model could read its own code, run benchmarks, and rewrite itself across 10 iterations. Then we compared the final bots head to head. Qwen 3.7-Max: training cost $1.32, bot improvement +56% Claude Opus 4.7: training cost $12.15, bot improvement +28% GPT-5.5: training cost $2.85, bot improvement +7% Qwen won on every dimension - biggest jump, 9× cheaper than Claude, 2× cheaper than GPT. Long agentic loops is where Qwen Max actually delivers.

Qwen 3.7-max beats Opus 4.7 and GPT-5.5 We tested three frontier models on a real agentic task: write a Tetris bot that plays the game and trains itself. Each model could read its own code, run benchmarks, and rewrite itself across 10 iterations. Then we compared the final bots head to head. Qwen 3.7-Max: training cost $1.32, bot improvement +56% Claude Opus 4.7: training cost $12.15, bot improvement +28% GPT-5.5: training cost $2.85, bot improvement +7% Qwen won on every dimension - biggest jump, 9× cheaper than Claude, 2× cheaper than GPT. Long agentic loops is where Qwen Max actually delivers.

870,741 просмотров

Nemotron 3 Ultra performed GPT 5.5 level 10× cheaper We gave three same prompts to build HTML5 canvas with real physics. At first scene we have water in a spinning drum. Galton board - balls through pegs into bins. And a block collision setup with extreme mass differences. Outputs: Nemotron 3 Ultra: 11.3k tokens, $0.051 GPT 5.5: 11.0k tokens, $0.57 Nemotron stays right on GPT 5.5's heels, but at 10× cheaper. The gap in quality is far smaller than the gap in price.

Nemotron 3 Ultra performed GPT 5.5 level 10× cheaper We gave three same prompts to build HTML5 canvas with real physics. At first scene we have water in a spinning drum. Galton board - balls through pegs into bins. And a block collision setup with extreme mass differences. Outputs: Nemotron 3 Ultra: 11.3k tokens, $0.051 GPT 5.5: 11.0k tokens, $0.57 Nemotron stays right on GPT 5.5's heels, but at 10× cheaper. The gap in quality is far smaller than the gap in price.

701,864 просмотров

Mistral OCR 4 turned a handwritten calculus exam into clean LaTeX! We gave it a photo of a hand-written exam page. The model read the handwriting and rebuilt every formula into structured digital text Output: Time: 5.1s · Cost: $0.09 Formulas came through exactly right - the hard part was nailed. The graph, unfortunately, it didn’t redraw. But that’s the telling part: most OCR tools just dump the text and quietly drop the figure. OCR 4 caught the plot, boxed it, and tagged it as a chart. It doesn’t get redrawn, but it gets read and accounted for

Mistral OCR 4 turned a handwritten calculus exam into clean LaTeX! We gave it a photo of a hand-written exam page. The model read the handwriting and rebuilt every formula into structured digital text Output: Time: 5.1s · Cost: $0.09 Formulas came through exactly right - the hard part was nailed. The graph, unfortunately, it didn’t redraw. But that’s the telling part: most OCR tools just dump the text and quietly drop the figure. OCR 4 caught the plot, boxed it, and tagged it as a chart. It doesn’t get redrawn, but it gets read and accounted for

421,714 просмотров

Local Laya blitzed other models on RTX 4090 ⚡️ Four local decision models raced down Wikipedia picking out every word that names a centipede and Laya took 3.9 ms a word so it ended up being the fastest overall Run decision models locally ->

Local Laya blitzed other models on RTX 4090 ⚡️ Four local decision models raced down Wikipedia picking out every word that names a centipede and Laya took 3.9 ms a word so it ended up being the fastest overall Run decision models locally ->

26,773 просмотров

TensorRT 206% faster than llama.cpp ✳️ We wired NVIDIA AI's TensorRT into Atomic Chat's engine and tested Qwen3.5-4B/Qwen 3-8B via CUDA on a Blackwell RTX 5090, measuring 3.43s vs 10.49s with llama.cpp Run AI models locally ->

TensorRT 206% faster than llama.cpp ✳️ We wired NVIDIA AI's TensorRT into Atomic Chat's engine and tested Qwen3.5-4B/Qwen 3-8B via CUDA on a Blackwell RTX 5090, measuring 3.43s vs 10.49s with llama.cpp Run AI models locally ->

29,651 просмотров

Space Bunny Alpha mogged by DeepSeek V4.1 Flash 🐳 We asked both to build Minecraft in one HTML file and DeepSeek V4.1 Flash made a forest biome you can walk and dig in while Space Bunny Alpha's ground has holes showing the sky Run AI models locally ->

Space Bunny Alpha mogged by DeepSeek V4.1 Flash 🐳 We asked both to build Minecraft in one HTML file and DeepSeek V4.1 Flash made a forest biome you can walk and dig in while Space Bunny Alpha's ground has holes showing the sky Run AI models locally ->

50,419 просмотров

Running MiniCPM5-2B locally on a 16GB MacBook 💻 It beats Qwen3.5-4B on benchmarks, so we asked it to find recent AI news, it called web search, pulled back 10 results and summarized the key developments inside Atomic Chat Run local models via

Running MiniCPM5-2B locally on a 16GB MacBook 💻 It beats Qwen3.5-4B on benchmarks, so we asked it to find recent AI news, it called web search, pulled back 10 results and summarized the key developments inside Atomic Chat Run local models via

63,973 просмотров

Run Uncensored Qwen-Image 2.1 on 16GB Mac Qwen's image model with no filters makes the images cloud apps refuse and your prompts never leave your Mac, all of it done locally Run AI models locally ->

Run Uncensored Qwen-Image 2.1 on 16GB Mac Qwen's image model with no filters makes the images cloud apps refuse and your prompts never leave your Mac, all of it done locally Run AI models locally ->

29,374 просмотров

MTP speedup Qwen by 2.5x in Atomic Chat Dense vs MoE models on 2x RTX 5090 Qwen3.6 27B: 51 → 117 tps +137% Qwen3.6 35B-A3B: 218 → 267 tps +25% MTP drafts several tokens ahead and verifies them in one pass. The speedup depends on memory moved per pass. Dense 27B reads all 27B params per token, MoE 35B-A3B only reads 3B active. Dense had way more to save by batching. The baseline tps also differ (218 vs 51) for the same reason from the other side. Token generation is memory-bandwidth bound, and MoE moves ~8x less memory per token, so its baseline is already 4x ahead. ~80% draft acceptance. Zero accuracy loss. ~1 GB extra VRAM. Open-source code and local AI app – in the comments 👇

MTP speedup Qwen by 2.5x in Atomic Chat Dense vs MoE models on 2x RTX 5090 Qwen3.6 27B: 51 → 117 tps +137% Qwen3.6 35B-A3B: 218 → 267 tps +25% MTP drafts several tokens ahead and verifies them in one pass. The speedup depends on memory moved per pass. Dense 27B reads all 27B params per token, MoE 35B-A3B only reads 3B active. Dense had way more to save by batching. The baseline tps also differ (218 vs 51) for the same reason from the other side. Token generation is memory-bandwidth bound, and MoE moves ~8x less memory per token, so its baseline is already 4x ahead. ~80% draft acceptance. Zero accuracy loss. ~1 GB extra VRAM. Open-source code and local AI app – in the comments 👇

171,139 просмотров

New Hunyuan Hy3 hits Gemini 3.5 quality on physics for 35x cheaper! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics demos Prompts: - A bowling ball knocking down the pins - An air hockey rally that ends in a goal - A pool break scattering the rack Outputs: Hunyuan Hy3: 29,757 tokens, $0.006 Gemini 3.5: 23,300 tokens, $0.21 GLM-5.2: 25,454 tokens, $0.07 DeepSeek-V4: 50,600 tokens, $0.009 Tencent's Hy3 matched Gemini across all three: clean collisions, the puck bounced true, the pins scattered like a real strike, the rack broke with real momentum, nothing clipped or floated. GLM is genuinely strong on pure coding tasks, but the moment the job steps outside clean code it gives way. DeepSeek was the letdown, it burned the most tokens of anyone (50k, almost 2x Hy3) and still turned in the weakest scenes

New Hunyuan Hy3 hits Gemini 3.5 quality on physics for 35x cheaper! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics demos Prompts: - A bowling ball knocking down the pins - An air hockey rally that ends in a goal - A pool break scattering the rack Outputs: Hunyuan Hy3: 29,757 tokens, $0.006 Gemini 3.5: 23,300 tokens, $0.21 GLM-5.2: 25,454 tokens, $0.07 DeepSeek-V4: 50,600 tokens, $0.009 Tencent's Hy3 matched Gemini across all three: clean collisions, the puck bounced true, the pins scattered like a real strike, the rack broke with real momentum, nothing clipped or floated. GLM is genuinely strong on pure coding tasks, but the moment the job steps outside clean code it gives way. DeepSeek was the letdown, it burned the most tokens of anyone (50k, almost 2x Hy3) and still turned in the weakest scenes

112,224 просмотров

LongCat performed Opus 4.8 and GPT 5.5 level on real physics tasks for $0! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics Prompts: - A cannon demolishing a brick wall - A bowling ball knocking down the pins - A tornado that sucks in random objects Outputs: LongCat: 18,015 tokens, $0.00 Opus 4.8: 18,872 tokens, $0.48 GPT 5.5: 32,588 tokens, $0.98 GLM 5.2: 31,062 tokens, $0.09 On the physics LongCat came out ahead of Opus 4.8 and GLM 5.2 - cleaner collisions, nothing clipping or falling through. On detail and rendering it matched GPT 5.5, the best looking of the four. Getting this quality for free is wild!

LongCat performed Opus 4.8 and GPT 5.5 level on real physics tasks for $0! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics Prompts: - A cannon demolishing a brick wall - A bowling ball knocking down the pins - A tornado that sucks in random objects Outputs: LongCat: 18,015 tokens, $0.00 Opus 4.8: 18,872 tokens, $0.48 GPT 5.5: 32,588 tokens, $0.98 GLM 5.2: 31,062 tokens, $0.09 On the physics LongCat came out ahead of Opus 4.8 and GLM 5.2 - cleaner collisions, nothing clipping or falling through. On detail and rendering it matched GPT 5.5, the best looking of the four. Getting this quality for free is wild!

106,154 просмотров

Laguna S 2.1 performs at GLM-5.2 level on building popular games with 6x fewer params! We gave three local models the same task: build three popular arcade games that play themselves. Each game is one self-contained HTML file with a bot that plays it. Prompts: – Geometry Dash – Doodle Jump – Air Hockey Outputs: Laguna S 2.1: 10.3K tokens GLM-5.2: 26.4K tokens Hy3: 10.4K tokens Laguna held its quality against a 753B model. We think Laguna's Geometry Dash looked the best of the three, the cube clears every spike and block. GLM won Air Hockey. Its table looked the most detailed of all. Hy3 was the only model that added shooting to its Doodle Jump. But Laguna is the only model in our benchmark that runs on a MacBook with 128GB!

Laguna S 2.1 performs at GLM-5.2 level on building popular games with 6x fewer params! We gave three local models the same task: build three popular arcade games that play themselves. Each game is one self-contained HTML file with a bot that plays it. Prompts: – Geometry Dash – Doodle Jump – Air Hockey Outputs: Laguna S 2.1: 10.3K tokens GLM-5.2: 26.4K tokens Hy3: 10.4K tokens Laguna held its quality against a 753B model. We think Laguna's Geometry Dash looked the best of the three, the cube clears every spike and block. GLM won Air Hockey. Its table looked the most detailed of all. Hy3 was the only model that added shooting to its Doodle Jump. But Laguna is the only model in our benchmark that runs on a MacBook with 128GB!

66,917 просмотров

Grok 4.5 performed GPT Sol level for free! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics demos Prompts: -robot deathmatch, Tombstone vs Minotaur -a hydraulic press flattening stuff on a conveyor -a semi truck jumping a canyon Outputs: GPT-5.6 Sol: 12.9K tokens, $0.51 (~7 min) Grok 4.5: 10.8K tokens, $0 (~5 min) Muse Spark 1.1: 26.8K tokens, $0.12 (~7.5 min) GLM 5.2: 10.9K tokens, $0.02 (~12 min) Grok 4.5 handled all three scenes genuinely well and got surprisingly close to GPT-5.6 this round. On top of that, it ran on the free tier. GPT-5.6 Sol, the frontier model, put out solid but not standout work. GLM 5.2 rendered all three scenes for pennies, but it came out the roughest of the four. Meta's new Muse Spark burned the most tokens yet still stayed cheap, delivering an average result.

Grok 4.5 performed GPT Sol level for free! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics demos Prompts: -robot deathmatch, Tombstone vs Minotaur -a hydraulic press flattening stuff on a conveyor -a semi truck jumping a canyon Outputs: GPT-5.6 Sol: 12.9K tokens, $0.51 (~7 min) Grok 4.5: 10.8K tokens, $0 (~5 min) Muse Spark 1.1: 26.8K tokens, $0.12 (~7.5 min) GLM 5.2: 10.9K tokens, $0.02 (~12 min) Grok 4.5 handled all three scenes genuinely well and got surprisingly close to GPT-5.6 this round. On top of that, it ran on the free tier. GPT-5.6 Sol, the frontier model, put out solid but not standout work. GLM 5.2 rendered all three scenes for pennies, but it came out the roughest of the four. Meta's new Muse Spark burned the most tokens yet still stayed cheap, delivering an average result.

70,490 просмотров

Liquid's LFM2.5-8B-A1B smashed OpenAI's gpt-oss-20b on tool calling We ran both locally on a MacBook Pro M5 Max, 64GB, and gave each the same trip-planning request that only completes if the model fires all 7 tool calls - weather for 3 cities, two currency conversions, an email and a reminder Outputs: LFM2.5-8B-A1B: 4.8 GB RAM usage, 7/7 tool-calls, 266 tok/s, 6.9s OpenAI gpt-oss-20b: 11 GB RAM usage, 3/7 tool-calls, 146 tok/s, 15.0s The 8B used less than half the RAM and still fired all 7 calls, while the 20B silently dropped more than half of its own. It also ran ~2x faster, wrapping the full agentic request in 6.9s against 15s. That's what 38T training tokens buy: a 1B-active MoE that nails the agentic tool calls a model 2.5x its active size keeps dropping

Liquid's LFM2.5-8B-A1B smashed OpenAI's gpt-oss-20b on tool calling We ran both locally on a MacBook Pro M5 Max, 64GB, and gave each the same trip-planning request that only completes if the model fires all 7 tool calls - weather for 3 cities, two currency conversions, an email and a reminder Outputs: LFM2.5-8B-A1B: 4.8 GB RAM usage, 7/7 tool-calls, 266 tok/s, 6.9s OpenAI gpt-oss-20b: 11 GB RAM usage, 3/7 tool-calls, 146 tok/s, 15.0s The 8B used less than half the RAM and still fired all 7 calls, while the 20B silently dropped more than half of its own. It also ran ~2x faster, wrapping the full agentic request in 6.9s against 15s. That's what 38T training tokens buy: a 1B-active MoE that nails the agentic tool calls a model 2.5x its active size keeps dropping

92,187 просмотров

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Local Laya moggs Jev at Grok 4.7-built Tetris 🧩 An open-weights System One model called Laya, beat cloud-based Jev at playing Tetris by making decisions 11 times faster, running locally on a 16GB MacBook Air! Run AI models locally ->

Local Laya moggs Jev at Grok 4.7-built Tetris 🧩 An open-weights System One model called Laya, beat cloud-based Jev at playing Tetris by making decisions 11 times faster, running locally on a 16GB MacBook Air! Run AI models locally ->

1,098,057 просмотров • 27 дней назад

Claude Haiku 5.5 cost 12x more than GPT-6 Luna for the same scene 🐉 Both have the same API price, yet building the same animated voxel 3D pagoda island cost $24.96 on Claude Haiku 5.5 and $1.91 on GPT-6 Luna Run both models via API ->

Claude Haiku 5.5 cost 12x more than GPT-6 Luna for the same scene 🐉 Both have the same API price, yet building the same animated voxel 3D pagoda island cost $24.96 on Claude Haiku 5.5 and $1.91 on GPT-6 Luna Run both models via API ->

383,158 просмотров • 12 дней назад

Local Laya beat OpenAI's decision API 🕷 Four decision models raced down a web page ripping out links that name a spider and Laya running locally on an M5 Max took 34 ms a link so it checked 3x more than the cloud models Run decision models locally ->

Local Laya beat OpenAI's decision API 🕷 Four decision models raced down a web page ripping out links that name a spider and Laya running locally on an M5 Max took 34 ms a link so it checked 3x more than the cloud models Run decision models locally ->

216,880 просмотров • 12 дней назад

Local Liquid d1 3B crushed OpenAI Decision at Snake 🐍 Liquid AI d1 on a single RTX 3090 decides in 8 ms so its snake made 82 moves a second and ate 86 apples while OpenAI's API took 345 ms a call and ate 3 Run decision models ->

Local Liquid d1 3B crushed OpenAI Decision at Snake 🐍 Liquid AI d1 on a single RTX 3090 decides in 8 ms so its snake made 82 moves a second and ate 86 apples while OpenAI's API took 345 ms a call and ate 3 Run decision models ->

194,199 просмотров • 12 дней назад

Opus 5 crushed Fable 5 at 3D destruction physics for 2x cheaper! We gave four models the same task: build three self-contained HTML scenes with real physics Prompts: - A tornado that sucks in a whole field - A wrecking ball taking down an apartment block - An overloaded truck collapsing a truss bridge Outputs: - Opus 5: 55.9K tokens, $1.40 - Fable 5: 55.1K tokens, $2.82 - Kimi K3: 35.7K tokens, $0.55 - GPT 5.6: 20.1K tokens, $0.31 Opus got all three right unlike the other models. Houses fly up the funnel and out the top, the wall breaks where the ball hits and the rubble piles up, the bridge drops the truck into the river. Fable had almost nothing on the ground for the tornado to pick up, its building collapsed on its own before the ball even touched it and its bridge blew into sticks all at once. GPT is the cheapest here but its ball never reached the building at all and its bridge fell apart in a way nothing falls apart in real life. Kimi K3, the new Chinese frontier model, ended up in the same place as GPT

Opus 5 crushed Fable 5 at 3D destruction physics for 2x cheaper! We gave four models the same task: build three self-contained HTML scenes with real physics Prompts: - A tornado that sucks in a whole field - A wrecking ball taking down an apartment block - An overloaded truck collapsing a truss bridge Outputs: - Opus 5: 55.9K tokens, $1.40 - Fable 5: 55.1K tokens, $2.82 - Kimi K3: 35.7K tokens, $0.55 - GPT 5.6: 20.1K tokens, $0.31 Opus got all three right unlike the other models. Houses fly up the funnel and out the top, the wall breaks where the ball hits and the rubble piles up, the bridge drops the truck into the river. Fable had almost nothing on the ground for the tornado to pick up, its building collapsed on its own before the ball even touched it and its bridge blew into sticks all at once. GPT is the cheapest here but its ball never reached the building at all and its bridge fell apart in a way nothing falls apart in real life. Kimi K3, the new Chinese frontier model, ended up in the same place as GPT

1,484,523 просмотров • 2 месяцев назад

Le Chonk enters the Frontier race 🐈 We put Mistral AI Large 4, MiMo V2.6 Pro, Opus 5.5 and GPT-6.1 Sol side by side with voxel, ASCII, Blender and SVG remakes of the launch clip Run AI models locally and via API ->

Le Chonk enters the Frontier race 🐈 We put Mistral AI Large 4, MiMo V2.6 Pro, Opus 5.5 and GPT-6.1 Sol side by side with voxel, ASCII, Blender and SVG remakes of the launch clip Run AI models locally and via API ->

159,532 просмотров • 13 дней назад

Gemini 4 Argon is Opus 5.5 level for 3x cheaper 💵 We put Google's latest model against opus 5.5 side by side to create a 3D Voxel sport car assembly animation Run both models via API ->

Gemini 4 Argon is Opus 5.5 level for 3x cheaper 💵 We put Google's latest model against opus 5.5 side by side to create a 3D Voxel sport car assembly animation Run both models via API ->

64,745 просмотров • 5 дней назад

OpenAI Decision crushed by Microsoft-Decision-1 at Space Invaders 👾 Decision-1 decided 3.5x faster so it scored 3,320 and cleared 4 waves while OpenAI's decision API scored 1,300 taking over 300ms per decision on average Run decision models ->

OpenAI Decision crushed by Microsoft-Decision-1 at Space Invaders 👾 Decision-1 decided 3.5x faster so it scored 3,320 and cleared 4 waves while OpenAI's decision API scored 1,300 taking over 300ms per decision on average Run decision models ->

91,043 просмотров • 9 дней назад

New Fable 5 beats Opus 4.8 on real world physics simulations We gave both models the same three prompts and asked them to build self contained HTML5 sims with real physics and no libraries: 1. Chaotic double pendulum 2. Galton board 3. Water in a spinning drum (WCSPH) Generation cost Fable 5: $3.35 on 68.7k tokens, time 14m 47s Opus 4.8: $0.93 on 38.9k tokens, time 8m 10s Fable clearly did better on the water simulation, producing a much more solid and continuous body of water. Opus left larger gaps near the walls, scattered particles around the scene, and struggled to keep the fluid stable.

New Fable 5 beats Opus 4.8 on real world physics simulations We gave both models the same three prompts and asked them to build self contained HTML5 sims with real physics and no libraries: 1. Chaotic double pendulum 2. Galton board 3. Water in a spinning drum (WCSPH) Generation cost Fable 5: $3.35 on 68.7k tokens, time 14m 47s Opus 4.8: $0.93 on 38.9k tokens, time 8m 10s Fable clearly did better on the water simulation, producing a much more solid and continuous body of water. Opus left larger gaps near the walls, scattered particles around the scene, and struggled to keep the fluid stable.

1,588,276 просмотров • 4 месяцев назад

GPT 6.1 Sol 30x cheaper than Sonnet 5.5 at 3D ⚙️ openAI just dropped GPT 6.1 Sol, we put it up against Sonnet 5.5 and made them create a 3D keyboard assembly video in Three.js Run both models via sub ->

GPT 6.1 Sol 30x cheaper than Sonnet 5.5 at 3D ⚙️ openAI just dropped GPT 6.1 Sol, we put it up against Sonnet 5.5 and made them create a 3D keyboard assembly video in Three.js Run both models via sub ->

196,281 просмотров • 20 дней назад

GPT-5.6 Sol Ultra lost to GPT-5.5 on physics at 3× the cost! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics demos Prompts: - A monster truck backflipping onto a parked car - A stunt car jumping six buses into a brick wall - A train derailing off a broken bridge into the water Outputs: GPT-5.6 Sol Ultra: 32.9K tokens, $0.33 Opus 4.8: 9.2K tokens, $0.24 GPT-5.5: 12.4K tokens, $0.11 Grok 4.5: 7.0K tokens, $0.08 Sol Ultra draws just like GPT-5.5, only with more detail and it shows clearest on the bus jump where the two look almost identical. In the other tests Sol Ultra came out worse than its predecessor and the physics really got weaker. We think GPT-5.5 took the truck flip and the train outright. With Sol Ultra you basically get GPT-5.5 with weaker physics and a nicer picture for 3x the price. Newborn Grok 4.5 failed two of the three tests and only came good on the train

GPT-5.6 Sol Ultra lost to GPT-5.5 on physics at 3× the cost! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics demos Prompts: - A monster truck backflipping onto a parked car - A stunt car jumping six buses into a brick wall - A train derailing off a broken bridge into the water Outputs: GPT-5.6 Sol Ultra: 32.9K tokens, $0.33 Opus 4.8: 9.2K tokens, $0.24 GPT-5.5: 12.4K tokens, $0.11 Grok 4.5: 7.0K tokens, $0.08 Sol Ultra draws just like GPT-5.5, only with more detail and it shows clearest on the bus jump where the two look almost identical. In the other tests Sol Ultra came out worse than its predecessor and the physics really got weaker. We think GPT-5.5 took the truck flip and the train outright. With Sol Ultra you basically get GPT-5.5 with weaker physics and a nicer picture for 3x the price. Newborn Grok 4.5 failed two of the three tests and only came good on the train

898,646 просмотров • 3 месяцев назад

New Opus 4.8 crashed Opus 4.7 at physics on canvas! We gave both models the same three prompts: simulate a real physics phenomenon on raw HTML5 canvas. Prompt 1: "A triple pendulum swings into chaos and paints glowing trails with its tip" Prompt 2: "A 1 kg block bounces between a wall and a 100.000 kg block. The collisions count out the digits of pi" Prompt 3: "Balls fall through a grid of pegs and pile into a bell curve"

New Opus 4.8 crashed Opus 4.7 at physics on canvas! We gave both models the same three prompts: simulate a real physics phenomenon on raw HTML5 canvas. Prompt 1: "A triple pendulum swings into chaos and paints glowing trails with its tip" Prompt 2: "A 1 kg block bounces between a wall and a 100.000 kg block. The collisions count out the digits of pi" Prompt 3: "Balls fall through a grid of pegs and pile into a bell curve"

638,712 просмотров • 4 месяцев назад

Ling 3.1 Flash running locally beat GPT-6 Luna at LEGO Eiffel Tower 🧱 Ant Ling just dropped Ling 3.1 Flash open weights and it crushed GPT-6 Luna on the same Three.js prompt for 2.8x cheaper Run AI models locally ->

Ling 3.1 Flash running locally beat GPT-6 Luna at LEGO Eiffel Tower 🧱 Ant Ling just dropped Ling 3.1 Flash open weights and it crushed GPT-6 Luna on the same Three.js prompt for 2.8x cheaper Run AI models locally ->

20,933 просмотров • 4 дней назад

Agent Zero crushed Codex by 2.6× on token efficiency! We gave both agents the same task on the same local model (Qwen3.6 27B): build a retro Q*bert arcade game. Each agent wrote and rewrote it across iterations, adding enemies and a HUD. Outputs: • Agent Zero: 239K tokens, 53 min • Codex: 627K tokens, 51 min Both agents built a working Q*bert, but Gitlawb 's Agent Zero is the cleaner build, with crisper textures and hops that land where they should. Codex refills the context window with its whole history every turn, so the model loses the thread and hallucinates code it never wrote. Agent Zero sends only what's new, so it keeps more of the window open and makes fewer mistakes. Run agents on local AI models in Atomic Chat!

Agent Zero crushed Codex by 2.6× on token efficiency! We gave both agents the same task on the same local model (Qwen3.6 27B): build a retro Qbert arcade game. Each agent wrote and rewrote it across iterations, adding enemies and a HUD. Outputs: • Agent Zero: 239K tokens, 53 min • Codex: 627K tokens, 51 min Both agents built a working Qbert, but Gitlawb 's Agent Zero is the cleaner build, with crisper textures and hops that land where they should. Codex refills the context window with its whole history every turn, so the model loses the thread and hallucinates code it never wrote. Agent Zero sends only what's new, so it keeps more of the window open and makes fewer mistakes. Run agents on local AI models in Atomic Chat!

320,509 просмотров • 2 месяцев назад

GPT-6 Astra smokes Claude Fable 5.1 in Blender 💨 We compared GPT-6 Astra and Fable 5.1 on a Porsche 911 GT3 RS build and the difference is visible from the very first shot Output: Astra: $132.03 • 2.58 hours Fable: $114.41 • 2.56 hours Astra's model is not only more detailed in every aspect, but also far closer to the original car, costing almost the same as Fable's blocky funny looking model, the difference is astonishing

GPT-6 Astra smokes Claude Fable 5.1 in Blender 💨 We compared GPT-6 Astra and Fable 5.1 on a Porsche 911 GT3 RS build and the difference is visible from the very first shot Output: Astra: $132.03 • 2.58 hours Fable: $114.41 • 2.56 hours Astra's model is not only more detailed in every aspect, but also far closer to the original car, costing almost the same as Fable's blocky funny looking model, the difference is astonishing

133,234 просмотров • 1 месяц назад

MiniCPM-V 4.7 beat Qwen 3.6 35B-3A at Pagoda 🏯 OpenBMB's new 35B-A3 model made a better 3D Voxel Japanese Pagoda while consuming 10% less tokens than Qwen 3.6 35B-3A Run AI models locally ->

MiniCPM-V 4.7 beat Qwen 3.6 35B-3A at Pagoda 🏯 OpenBMB's new 35B-A3 model made a better 3D Voxel Japanese Pagoda while consuming 10% less tokens than Qwen 3.6 35B-3A Run AI models locally ->

22,419 просмотров • 7 дней назад

Qwen 3.8 Max beat Fable 5 at building 3D physics scenes for 7x cheaper! We gave two models the same task. Build three self-contained 3D scenes, each one HTML file with real physics that runs itself. Prompts: - A marble machine that lifts marbles up a wheel and drops them on a loop - A car factory assembly line - A sawmill cutting logs into planks Outputs: Qwen 3.8 Max: 46.6K tokens, $0.28 Fable 5: 38.7K tokens, $1.93 Qwen worked much harder on the details. Its textures and shadows look real. Fable 5 built a fast prototype that works and left it there. In the marble machine, Fable's marbles show up from nowhere at the top of the wheel. In Qwen's, you can see them go up. On the car line, Qwen's cars look much better and more real. Fable's sawmill is very strange. The saw looks wrong, and the log goes right through a beam before the saw cuts it. Atomic Chat will have day zero support to run Qwen 3.8 Max locally!

Sensitive content

This media may contain sensitive content.

Qwen 3.8 Max beat Fable 5 at building 3D physics scenes for 7x cheaper! We gave two models the same task. Build three self-contained 3D scenes, each one HTML file with real physics that runs itself. Prompts: - A marble machine that lifts marbles up a wheel and drops them on a loop - A car factory assembly line - A sawmill cutting logs into planks Outputs: Qwen 3.8 Max: 46.6K tokens, $0.28 Fable 5: 38.7K tokens, $1.93 Qwen worked much harder on the details. Its textures and shadows look real. Fable 5 built a fast prototype that works and left it there. In the marble machine, Fable's marbles show up from nowhere at the top of the wheel. In Qwen's, you can see them go up. On the car line, Qwen's cars look much better and more real. Fable's sawmill is very strange. The saw looks wrong, and the log goes right through a beam before the saw cuts it. Atomic Chat will have day zero support to run Qwen 3.8 Max locally!

211,210 просмотров • 2 месяцев назад

Union Alpha lost to DeepSeek V4.1 Flash running locally on 2 DGX Sparks 🐳 DeepSeek v4.1 Flash beat Union Alpha, which is supposed to deliver frontier level performance, though real tasks show a completely different story Run AI models locally ->

Union Alpha lost to DeepSeek V4.1 Flash running locally on 2 DGX Sparks 🐳 DeepSeek v4.1 Flash beat Union Alpha, which is supposed to deliver frontier level performance, though real tasks show a completely different story Run AI models locally ->

79,581 просмотров • 1 месяц назад

Google Turbo Quant running Locally in Atomic Chat MacBook Air M4 16 GB Model: QWEN3.5-9B Context window: 50000 Summarising 20000 words in just seconds.. You can do 3x larger context window, processing 3x faster than before!

Google Turbo Quant running Locally in Atomic Chat MacBook Air M4 16 GB Model: QWEN3.5-9B Context window: 50000 Summarising 20000 words in just seconds.. You can do 3x larger context window, processing 3x faster than before!

436,840 просмотров • 6 месяцев назад

Local Laya blitzed other models on RTX 4090 ⚡️ Four local decision models raced down Wikipedia picking out every word that names a centipede and Laya took 3.9 ms a word so it ended up being the fastest overall Run decision models locally ->

Local Laya blitzed other models on RTX 4090 ⚡️ Four local decision models raced down Wikipedia picking out every word that names a centipede and Laya took 3.9 ms a word so it ended up being the fastest overall Run decision models locally ->

26,773 просмотров • 11 дней назад