Video yükleniyor...

Video Yüklenemedi

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

Ana Sayfaya Dön

Open-weight MiniMax M3 filled out a US customs form from a driver's license photo For this test we deployed MiniMax M3 Q4 using MLX-VLM on a Mac Studio M3 Ultra 512GB RAM. The model was tasked with reading a scanned document and an ID card photo, then completing a... show more

atomic.chat

11,239 subscribers

109,369 görüntüleme • 2 ay önce •via X (Twitter)

Haberler & Politika Eğitim Bilim & Teknoloji

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Compared MiniMax M3 against three other frontier open-source models: DeepSeek V4, Qwen 3.7 Max, and MiMo 2.5 Pro MiniMax M3 crashed others on: 1. collision physics 2. 3D pinball generation It was the only model that produced a result for the 3D pinball test For human motion rendering and hexagon sketching, Qwen 3.7 Max still tops

Compared MiniMax M3 against three other frontier open-source models: DeepSeek V4, Qwen 3.7 Max, and MiMo 2.5 Pro MiniMax M3 crashed others on: 1. collision physics 2. 3D pinball generation It was the only model that produced a result for the 3D pinball test For human motion rendering and hexagon sketching, Qwen 3.7 Max still tops

GMI Cloud

51,116 görüntüleme • 2 ay önce

GLM-5 runs with mlx-lm on a single 512GB M3 Ultra in Q4. It's quite good in my initial testing and pretty fast as well. It generated a highly functional space invaders game using 7.1k tokens at 15.4 tok/s and 419GB memory. Thanks to Gökdeniz Gülmez and Tarjei Mandt for the port.

GLM-5 runs with mlx-lm on a single 512GB M3 Ultra in Q4. It's quite good in my initial testing and pretty fast as well. It generated a highly functional space invaders game using 7.1k tokens at 15.4 tok/s and 419GB memory. Thanks to Gökdeniz Gülmez and Tarjei Mandt for the port.

Awni Hannun

60,599 görüntüleme • 6 ay önce

I designed a new test specifically for multimodal models: fill out a paper form. And it's much harder than it sounds. This isn't typing into an electronic field that captures your text. The form is just an image. The model has to place each form element: text, checkmarks — at the correct pixel position on the canvas itself. Results: 🟢 Kimi K2.6 → done in 3:45, 16.7k output tokens 🟡 Step 3.7 Flash → half the fields, 57k output tokens 🔴 Gemini 3.5 Flash → 489k output tokens, never finished. I had to kill it. Gemini burned ~29x more output tokens than Kimi on the exact same task, and Kimi's was the only form that actually looked filled out. The test, a mocked application form, contains some challenging parts, such as one-character-per-box fields. I provided every model the same set of tools: > get canvas size > drop probe markers to find coordinates > add text > add checkmarks > move elements > take a screenshot anytime to check their own work > ... etc So it's vision + spatial reasoning + tool use + long context, all at once. Small models (Qwen, Gemma) can't really complete this test, so I skipped them. What happened: > Kimi nailed name, DOB, ID, gender, marital status, nationality, email, phone, address, postal code — placement slightly loose, but content correct. 15 turns. Clean. > Step got maybe half right — fields dropped, "United States" landed in the email line, data floating outside boxes. Burned 1.24M input tokens doing it (81 turns of re-reading the canvas). > Gemini almost got there visually... then spiraled. By turn 40 it was issuing a delete_elements call wiping element IDs 365–425, basically erasing its own work. 31 minutes, 489k output tokens, still streaming. Terminated. The takeaway isn't "Gemini bad." This test is indeed difficult. But token efficiency is capability now. A model that needs 30x the tokens and still can't converge is going to be 30x the cost in production. Kimi K2.6 just quietly did the thing.

I designed a new test specifically for multimodal models: fill out a paper form. And it's much harder than it sounds. This isn't typing into an electronic field that captures your text. The form is just an image. The model has to place each form element: text, checkmarks — at the correct pixel position on the canvas itself. Results: 🟢 Kimi K2.6 → done in 3:45, 16.7k output tokens 🟡 Step 3.7 Flash → half the fields, 57k output tokens 🔴 Gemini 3.5 Flash → 489k output tokens, never finished. I had to kill it. Gemini burned ~29x more output tokens than Kimi on the exact same task, and Kimi's was the only form that actually looked filled out. The test, a mocked application form, contains some challenging parts, such as one-character-per-box fields. I provided every model the same set of tools: > get canvas size > drop probe markers to find coordinates > add text > add checkmarks > move elements > take a screenshot anytime to check their own work > ... etc So it's vision + spatial reasoning + tool use + long context, all at once. Small models (Qwen, Gemma) can't really complete this test, so I skipped them. What happened: > Kimi nailed name, DOB, ID, gender, marital status, nationality, email, phone, address, postal code — placement slightly loose, but content correct. 15 turns. Clean. > Step got maybe half right — fields dropped, "United States" landed in the email line, data floating outside boxes. Burned 1.24M input tokens doing it (81 turns of re-reading the canvas). > Gemini almost got there visually... then spiraled. By turn 40 it was issuing a delete_elements call wiping element IDs 365–425, basically erasing its own work. 31 minutes, 489k output tokens, still streaming. Terminated. The takeaway isn't "Gemini bad." This test is indeed difficult. But token efficiency is capability now. A model that needs 30x the tokens and still can't converge is going to be 30x the cost in production. Kimi K2.6 just quietly did the thing.

stevibe

25,455 görüntüleme • 2 ay önce

$Everyone's sleeping on MiniMax. Again. They just shipped M3. The first open-weights model to combine frontier coding, 1M context, and native multimodality in one drop. I plugged it into Claude Code this morning. Pasted a design from Dribbble. Watched M3 write production-ready React code in one session. At the agency, I just replaced Opus 4.8 with M3 for 80% of our coding tasks. The output is the same and we are running everything at a fraction of the cost. Open infrastructure is the future.$

Everyone's sleeping on MiniMax. Again. They just shipped M3. The first open-weights model to combine frontier coding, 1M context, and native multimodality in one drop. I plugged it into Claude Code this morning. Pasted a design from Dribbble. Watched M3 write production-ready React code in one session. At the agency, I just replaced Opus 4.8 with M3 for 80% of our coding tasks. The output is the same and we are running everything at a fraction of the cost. Open infrastructure is the future.

Prajwal Tomar

12,904 görüntüleme • 2 ay önce

I plugged MiniMax (official) M3 into Claude Code in under 5 minutes and gave it a real task. most models need hand-holding every few steps. M3 ran 147 iterations on its own. what it actually did: → took a broken CUDA kernel → ran it for 24 hours, autonomously → pushed hardware efficiency from 7.6% to 71.3% → shipped a 9.4x speedup I didn't touch it once across that whole window. the rest of the spec sheet: → 1M token context window → native multimodal from day one → fully open weights pricing: → $20/month for 1.7B tokens → $50/month for 5.1B tokens → text, image, speech, and music all share one pool usually with this kind of capability the bill catches up fast. M3 keeps both lines low at the same time. that's the part that surprised me. and if this is what M3 does at launch, the full rollout is going to be one to watch. what would you build with 1M context? #MiniMax #MiniMaxM3 #ClaudeCode #LLM

I plugged MiniMax (official) M3 into Claude Code in under 5 minutes and gave it a real task. most models need hand-holding every few steps. M3 ran 147 iterations on its own. what it actually did: → took a broken CUDA kernel → ran it for 24 hours, autonomously → pushed hardware efficiency from 7.6% to 71.3% → shipped a 9.4x speedup I didn't touch it once across that whole window. the rest of the spec sheet: → 1M token context window → native multimodal from day one → fully open weights pricing: → $20/month for 1.7B tokens → $50/month for 5.1B tokens → text, image, speech, and music all share one pool usually with this kind of capability the bill catches up fast. M3 keeps both lines low at the same time. that's the part that surprised me. and if this is what M3 does at launch, the full rollout is going to be one to watch. what would you build with 1M context? #MiniMax #MiniMaxM3 #ClaudeCode #LLM

Nelly;

17,576 görüntüleme • 2 ay önce

Agentic Document Extraction now supports field extraction! Many doc extraction use cases extract specific fields from forms and other structured documents. You can now input a picture or PDF of an invoice, request the vendor name, item list, and prices, and get back the extracted fields. Or input a medical form and specify a schema to extract patient name, patient ID, insurance number, etc. One cool feature: If you don't feel like writing a schema (json specification of what fields to extract) yourself, upload one sample document and write a natural language prompt saying what you want, and we automatically generate a schema for you. See the video for details!

Agentic Document Extraction now supports field extraction! Many doc extraction use cases extract specific fields from forms and other structured documents. You can now input a picture or PDF of an invoice, request the vendor name, item list, and prices, and get back the extracted fields. Or input a medical form and specify a schema to extract patient name, patient ID, insurance number, etc. One cool feature: If you don't feel like writing a schema (json specification of what fields to extract) yourself, upload one sample document and write a natural language prompt saying what you want, and we automatically generate a schema for you. See the video for details!

Andrew Ng

193,053 görüntüleme • 1 yıl önce

NVIDIA sent us 2 DGX Sparks. For a while we wondered what we would do with them. The memory bandwidth is 273GB/s making it 3x slower than an M3 Ultra (819GB/s) for batch_size=1 inference. But it has 4x more FLOPS (100 TFLOPS compared to 26 TFLOPS). So we thought, what if we could combine the DGX Spark & M3 Ultra, and make use of both the massive compute on the DGX Spark and the massive memory-bandwidth on the M3 Ultra. We came up with a way to split inference across both devices and achieve a speedup of up to 4x for long prompts compared to the M3 Ultra on its own. Full details in the blog post linked below.

NVIDIA sent us 2 DGX Sparks. For a while we wondered what we would do with them. The memory bandwidth is 273GB/s making it 3x slower than an M3 Ultra (819GB/s) for batch_size=1 inference. But it has 4x more FLOPS (100 TFLOPS compared to 26 TFLOPS). So we thought, what if we could combine the DGX Spark & M3 Ultra, and make use of both the massive compute on the DGX Spark and the massive memory-bandwidth on the M3 Ultra. We came up with a way to split inference across both devices and achieve a speedup of up to 4x for long prompts compared to the M3 Ultra on its own. Full details in the blog post linked below.

Alex Cheema

281,225 görüntüleme • 10 ay önce

Check out the form-filling agent that automates PDF forms using AI by Jerry Liu 📄🤖 Use any fillable PDF with an agent that fills it out based on your prompts and context files. Our new experiment creates a multi-turn chat experience for form completion. 🔍 Upload fillable PDFs and automatically detect form fields using PyMuPDF 📝 Add custom prompts and context files (parsed via LlamaParse) to guide the AI 🤖 Multi-turn conversations let you refine and correct form entries after initial completion 💾 Download your completed forms when done The agent uses simple tools to list, set, get, and validate form fields. You can chat with it to make corrections and adjustments until your form is perfect. Check out the code on GitHub: Or the deployed app here:

Check out the form-filling agent that automates PDF forms using AI by Jerry Liu 📄🤖 Use any fillable PDF with an agent that fills it out based on your prompts and context files. Our new experiment creates a multi-turn chat experience for form completion. 🔍 Upload fillable PDFs and automatically detect form fields using PyMuPDF 📝 Add custom prompts and context files (parsed via LlamaParse) to guide the AI 🤖 Multi-turn conversations let you refine and correct form entries after initial completion 💾 Download your completed forms when done The agent uses simple tools to list, set, get, and validate form fields. You can chat with it to make corrections and adjustments until your form is perfect. Check out the code on GitHub: Or the deployed app here:

LlamaIndex 🦙

55,131 görüntüleme • 7 ay önce

GLM-4.7 runs quite well on an M3 Ultra with mlx-lm, even at a near lossless precision (6-bit here). It generated the best space invaders game I've seen yet for a local model (even included sound effects!). Generated 6600 tokens and ran at 16 tok/s.

GLM-4.7 runs quite well on an M3 Ultra with mlx-lm, even at a near lossless precision (6-bit here). It generated the best space invaders game I've seen yet for a local model (even included sound effects!). Generated 6600 tokens and ran at 16 tok/s.

Awni Hannun

237,191 görüntüleme • 8 ay önce

A self-evolving agent + a 428B model + 3 Macs = ? Your own AI lab. We ran MiniMax (official) M3 locally with Parallax, right on our desk. Then GenericAgent took over to create a 5-stock portfolio and write it to disk. No cloud. No API bills. Nothing left the machine. Wild to see a ~3K-line agent drive all this with a 400B+ model on local hardware. Thanks to the GenericAgent and MiniMax teams for making local AI feel real.

A self-evolving agent + a 428B model + 3 Macs = ? Your own AI lab. We ran MiniMax (official) M3 locally with Parallax, right on our desk. Then GenericAgent took over to create a 5-stock portfolio and write it to disk. No cloud. No API bills. Nothing left the machine. Wild to see a ~3K-line agent drive all this with a 400B+ model on local hardware. Thanks to the GenericAgent and MiniMax teams for making local AI feel real.

Gradient

151,211 görüntüleme • 1 ay önce

🎉 Congrats to MiniMax (official) on releasing MiniMax M3! Frontier coding and agentic capabilities, native image and video input, computer use, and a 1M-token context window, all in a single open model. At the heart of M3 is MSA, a new sparse attention architecture: instead of attending densely over the full KV cache, each query scores 128-token KV blocks and runs attention only over the top blocks. That is what makes 1M-token context practical to serve. M3 runs in vLLM with day-0 support, verified on NVIDIA and AMD hardware: ✨ MSA sparse attention with dedicated prefill and decode kernels ✨ 1M-token context serving with prefix caching and chunked prefill ✨ BF16 and MXFP8 checkpoints, with MoE backends for both Hopper and Blackwell ✨ Native multimodal input (image + video) ✨ Tool calling, reasoning parsing, and thinking-mode control for agent workloads Day-0 support like this is a true team effort. Grateful to the teams at MiniMax (official), NVIDIA AI, AI at AMD, and Inferact, and to the vLLM community for making it happen. 🙏 Deep dive into the implementation, kernel work, and deployment recipes: 🔗

🎉 Congrats to MiniMax (official) on releasing MiniMax M3! Frontier coding and agentic capabilities, native image and video input, computer use, and a 1M-token context window, all in a single open model. At the heart of M3 is MSA, a new sparse attention architecture: instead of attending densely over the full KV cache, each query scores 128-token KV blocks and runs attention only over the top blocks. That is what makes 1M-token context practical to serve. M3 runs in vLLM with day-0 support, verified on NVIDIA and AMD hardware: ✨ MSA sparse attention with dedicated prefill and decode kernels ✨ 1M-token context serving with prefix caching and chunked prefill ✨ BF16 and MXFP8 checkpoints, with MoE backends for both Hopper and Blackwell ✨ Native multimodal input (image + video) ✨ Tool calling, reasoning parsing, and thinking-mode control for agent workloads Day-0 support like this is a true team effort. Grateful to the teams at MiniMax (official), NVIDIA AI, AI at AMD, and Inferact, and to the vLLM community for making it happen. 🙏 Deep dive into the implementation, kernel work, and deployment recipes: 🔗

vLLM

40,306 görüntüleme • 2 ay önce

Built a fantasy RPG word-learning game with MiniMax M3. You defeat corrupted monsters by matching words correctly, while the game dynamically tracks mistakes, scales difficulty, unlocks elite remixes, and maintains progression systems across maps, continents, and boss fights. What stood out with M3 is that it could consistently handle long-context game logic, UI flow, progression balancing, and feature iteration without constantly breaking earlier systems. This is the first time an open model felt less like “prompt in, output out” and more like a system that can actually help maintain complex creative workflows.

Built a fantasy RPG word-learning game with MiniMax M3. You defeat corrupted monsters by matching words correctly, while the game dynamically tracks mistakes, scales difficulty, unlocks elite remixes, and maintains progression systems across maps, continents, and boss fights. What stood out with M3 is that it could consistently handle long-context game logic, UI flow, progression balancing, and feature iteration without constantly breaking earlier systems. This is the first time an open model felt less like “prompt in, output out” and more like a system that can actually help maintain complex creative workflows.

Darshal Jaitwar

31,254 görüntüleme • 2 ay önce

BMW M3, E92. 414 hp. From a 4.0L naturally aspirated V8. Revving to 8,400 rpm with no turbo. 0–100 km/h in around 4.6 seconds. Back then, 400 hp meant revs and sound in the 2000s. Not torque, not instant speed. This was about the experience, this car wanted you to rev the engine hard, this is a backroads car for going fast. One of the last naturally aspirated M3s. Compared to a modern M340i with maybe similar power, this feels slower, but this M3 is way better feeling and its a V8 M3, the only V8 M3 and the older M3's feel way way more alive.

BMW M3, E92. 414 hp. From a 4.0L naturally aspirated V8. Revving to 8,400 rpm with no turbo. 0–100 km/h in around 4.6 seconds. Back then, 400 hp meant revs and sound in the 2000s. Not torque, not instant speed. This was about the experience, this car wanted you to rev the engine hard, this is a backroads car for going fast. One of the last naturally aspirated M3s. Compared to a modern M340i with maybe similar power, this feels slower, but this M3 is way better feeling and its a V8 M3, the only V8 M3 and the older M3's feel way way more alive.

Autowelt

58,875 görüntüleme • 4 ay önce

new Ox Alpha is kind of absurd One prompt, 64,745 output tokens, and no external assets: Ox Alpha generated the code for an entire Three.js dreamcore 3D scene/world in a single shot. AI/ML API ran this demo and they are also giving Ox Alpha free on aimlapi[.]com - 1M context window - Max output: ~131k tokens - Multimodal: text + image + video input → text output - Explicitly positioned as a reasoning model for coding, long-horizon/agentic software engineering, sustained production workloads, and tasks that mix text with visual context

new Ox Alpha is kind of absurd One prompt, 64,745 output tokens, and no external assets: Ox Alpha generated the code for an entire Three.js dreamcore 3D scene/world in a single shot. AI/ML API ran this demo and they are also giving Ox Alpha free on aimlapi[.]com - 1M context window - Max output: ~131k tokens - Multimodal: text + image + video input → text output - Explicitly positioned as a reasoning model for coding, long-horizon/agentic software engineering, sustained production workloads, and tasks that mix text with visual context

Rohan Paul

13,576 görüntüleme • 5 gün önce

Hell froze over: announcing FormKit for React. Secretly framework-agnostic since inception, today we’re open sourcing the most popular Vue form library…for React. Why is this a big deal? 1. Forms are still hard. We (the creators of FormKit) thought form libraries were no longer necessary, given the trajectory of coding agents. It turns out we were wrong, and we learned this the hard way. Need repeating conditional fields nested 3 layers deep inside a dynamic component, with accessibility, validation, internationalization, and backend error placement? Turns out coding agents aren’t great at that. It’s table stakes for FormKit. 2. Single component. This matters more than you would think, but FormKit doesn’t ship lots of different components each with its own props. Instead, it has a single one: and unified props. This was done to provide a better DX to human engineers. It makes it easy to spot when a given component was part of the form’s data structure vs a presentational component. It turns out this matters even more to coding agents than humans. No matter where your coding agent is, whenever it sees “FormKit” it immediately knows “oh, that’s part of the form’s data”. 3. No plumbing. FormKit doesn’t require any manual data collection, event listening, or state tracking. It does all this for you on a heavily tested, framework agnostic, self-assembling graph. The only code your agent needs to write is declarative templates and submission handlers that respond to the state. 4. Dense colocation. FormKit’s syntax happens to be ideal for coding agents; nearly everything you need to know about a given input is *on* the input: Colocation dramatically improves the efficacy of coding agents. 5. DOM. FormKit, unlike most form frameworks in React, renders the actual DOM. This also increases colocation and best practices, meaning your coding agent is far more likely to produce consistent and high-quality output that looks and acts the way its supposed to. 6. Schema. FormKit’s own inputs are not written using Vue or React — instead, FormKit has its own render schema — think of it like an AST for the DOM — and you can modify it on the fly. It’s not very human-friendly to write, but it turns out most models are already pretty well trained on FormKit’s schema. Want your inputs to look a bit different on one form than another? No problem, your coding agent can easily make those changes *without* modifying the JSX structure at all. Oh, and any inputs you create for Vue work with React and vice versa. 7. Plugins. FormKit leans into the unstructured tree graph hard. The graph doesn’t just collect data, it also passes down configuration and plugins. Want one form to work a bit differently than another one? No problem — just add a plugin to the top of that form or group and its children will all receive that feature. You can even mass assign props and configuration this way. Of course, FormKit has been solving these exact issues for a long time, but it wasn’t until we started using it on our own projects with coding agents that we realized what a huge advantage it is. With so many people using coding agents with React, it made sense to unveil FormKit for what it has always been — a completely framework-agnostic form framework that happens to unlock your coding agents. ➡️

Hell froze over: announcing FormKit for React. Secretly framework-agnostic since inception, today we’re open sourcing the most popular Vue form library…for React. Why is this a big deal? 1. Forms are still hard. We (the creators of FormKit) thought form libraries were no longer necessary, given the trajectory of coding agents. It turns out we were wrong, and we learned this the hard way. Need repeating conditional fields nested 3 layers deep inside a dynamic component, with accessibility, validation, internationalization, and backend error placement? Turns out coding agents aren’t great at that. It’s table stakes for FormKit. 2. Single component. This matters more than you would think, but FormKit doesn’t ship lots of different components each with its own props. Instead, it has a single one: and unified props. This was done to provide a better DX to human engineers. It makes it easy to spot when a given component was part of the form’s data structure vs a presentational component. It turns out this matters even more to coding agents than humans. No matter where your coding agent is, whenever it sees “FormKit” it immediately knows “oh, that’s part of the form’s data”. 3. No plumbing. FormKit doesn’t require any manual data collection, event listening, or state tracking. It does all this for you on a heavily tested, framework agnostic, self-assembling graph. The only code your agent needs to write is declarative templates and submission handlers that respond to the state. 4. Dense colocation. FormKit’s syntax happens to be ideal for coding agents; nearly everything you need to know about a given input is on the input: Colocation dramatically improves the efficacy of coding agents. 5. DOM. FormKit, unlike most form frameworks in React, renders the actual DOM. This also increases colocation and best practices, meaning your coding agent is far more likely to produce consistent and high-quality output that looks and acts the way its supposed to. 6. Schema. FormKit’s own inputs are not written using Vue or React — instead, FormKit has its own render schema — think of it like an AST for the DOM — and you can modify it on the fly. It’s not very human-friendly to write, but it turns out most models are already pretty well trained on FormKit’s schema. Want your inputs to look a bit different on one form than another? No problem, your coding agent can easily make those changes without modifying the JSX structure at all. Oh, and any inputs you create for Vue work with React and vice versa. 7. Plugins. FormKit leans into the unstructured tree graph hard. The graph doesn’t just collect data, it also passes down configuration and plugins. Want one form to work a bit differently than another one? No problem — just add a plugin to the top of that form or group and its children will all receive that feature. You can even mass assign props and configuration this way. Of course, FormKit has been solving these exact issues for a long time, but it wasn’t until we started using it on our own projects with coding agents that we realized what a huge advantage it is. With so many people using coding agents with React, it made sense to unveil FormKit for what it has always been — a completely framework-agnostic form framework that happens to unlock your coding agents. ➡️

Justin Schroeder

11,677 görüntüleme • 4 ay önce

We just cracked document editing without drawing boxes. We’re excited to launch Edit – a new endpoint that fills out any document automatically. Edit revolutionizes document automation by automatically finding all blank fields, tables, and checkboxes in forms, then intelligently filling them with your data. To try it, sign up for the waitlist at or see it in action down below 🧵

We just cracked document editing without drawing boxes. We’re excited to launch Edit – a new endpoint that fills out any document automatically. Edit revolutionizes document automation by automatically finding all blank fields, tables, and checkboxes in forms, then intelligently filling them with your data. To try it, sign up for the waitlist at or see it in action down below 🧵

Reducto

260,110 görüntüleme • 1 yıl önce

MiniMax H3 is the SOTA open weight model... but the large model comes with slow gens (depending on your hardware). You can be waiting for minutes just for the generation to miss the mark Here's a ComfyUI workflow to get the most out of H3 without the wait. → H3 Turbo LoRA (4–8 steps) → Model Preview Override + Tiny AutoEncoder H3 for a fast composition preview → Bad preview? stop it, tweak the prompt or seed → Save your precious gpu time Workflow and model links below 👇

MiniMax H3 is the SOTA open weight model... but the large model comes with slow gens (depending on your hardware). You can be waiting for minutes just for the generation to miss the mark Here's a ComfyUI workflow to get the most out of H3 without the wait. → H3 Turbo LoRA (4–8 steps) → Model Preview Override + Tiny AutoEncoder H3 for a fast composition preview → Bad preview? stop it, tweak the prompt or seed → Save your precious gpu time Workflow and model links below 👇

rob - comfyui

26,990 görüntüleme • 15 gün önce

The MiniMax M2 model is mind-blowing! It's open-source. It outperforms Gemini 2.5, Claude 4.1, and Qwen3 across coding and tool-use benchmarks. Right now, it's one of the world's top 5 models in intelligence! And here is the best part: Claude is one of the best models you can use today, and MiniMax M2 costs only 8% of that! It's smaller, faster, and cheaper. Extremely efficient at using tokens. Minimax M2's biggest strength: High agentic capabilities. The model can plan and execute complex multi-tool workflows. It's reliable and very robust at executing long-horizon tool chains. In summary: • Low latency • Very cheap • Excels at agentic tasks • Open-source The model currently powers the MiniMax Agent and is available for a free global trial. You can access MiniMax M2's API here: To access the agent: And here is the MiniMax website: Thanks to the MiniMax team for showing me the ropes and partnering with me on this post.

The MiniMax M2 model is mind-blowing! It's open-source. It outperforms Gemini 2.5, Claude 4.1, and Qwen3 across coding and tool-use benchmarks. Right now, it's one of the world's top 5 models in intelligence! And here is the best part: Claude is one of the best models you can use today, and MiniMax M2 costs only 8% of that! It's smaller, faster, and cheaper. Extremely efficient at using tokens. Minimax M2's biggest strength: High agentic capabilities. The model can plan and execute complex multi-tool workflows. It's reliable and very robust at executing long-horizon tool chains. In summary: • Low latency • Very cheap • Excels at agentic tasks • Open-source The model currently powers the MiniMax Agent and is available for a free global trial. You can access MiniMax M2's API here: To access the agent: And here is the MiniMax website: Thanks to the MiniMax team for showing me the ropes and partnering with me on this post.

Santiago

91,197 görüntüleme • 10 ay önce

WORLD RECORD: 1990 BMW M3 Sport Evolution Following strong bidding at The Woodcote Park Auction, this exceptional 1990 BMW M3 Sport Evolution sold for a final price of £404,375, setting a new world auction record for the model. One of just 600 examples produced, this matching-numbers example is finished in its factory-correct Black over Black specification and displayed just 4,503 kilometres from new. Presented with a BMW Classic Birth Certificate and benefiting from specialist recommissioning, it ranks among the finest and lowest-mileage examples of the ultimate E30 M3. Sold for £404,375, a new world auction record. #RMWoodcotePark #RMSothebys #BMWM3 #E30M3

WORLD RECORD: 1990 BMW M3 Sport Evolution Following strong bidding at The Woodcote Park Auction, this exceptional 1990 BMW M3 Sport Evolution sold for a final price of £404,375, setting a new world auction record for the model. One of just 600 examples produced, this matching-numbers example is finished in its factory-correct Black over Black specification and displayed just 4,503 kilometres from new. Presented with a BMW Classic Birth Certificate and benefiting from specialist recommissioning, it ranks among the finest and lowest-mileage examples of the ultimate E30 M3. Sold for £404,375, a new world auction record. #RMWoodcotePark #RMSothebys #BMWM3 #E30M3

RM Sotheby's

19,534 görüntüleme • 1 ay önce

SITUATION EXPLAINED: A stealth model on OpenRouter is beating Fable and Sol on coding, and nobody knows who made it. • Ox Alpha has a 1M token context window, text, image, and video input, free for a week, with capacity for 100 trillion tokens a day • On a DeepSWE subset it hit 80%, against Fable's 65%, GLM-5.3's 62%, and Sol's 52% • The tokenizer is one-for-one identical to GLM's, and a live test asking whether Taiwan is part of China returned a nearly identical answer • This is the 5th anonymous drop in six months, and the previous four were all claimed by Chinese labs: Zhipu, Xiaomi, Ant, and Meituan Theo Jaffee: " There's no way it's a Flash model. If that's a Flash model, then holy shit, the entire United States is cooked. If that's a Flash model, we need to short the stock market now. Not financial advice."

SITUATION EXPLAINED: A stealth model on OpenRouter is beating Fable and Sol on coding, and nobody knows who made it. • Ox Alpha has a 1M token context window, text, image, and video input, free for a week, with capacity for 100 trillion tokens a day • On a DeepSWE subset it hit 80%, against Fable's 65%, GLM-5.3's 62%, and Sol's 52% • The tokenizer is one-for-one identical to GLM's, and a live test asking whether Taiwan is part of China returned a nearly identical answer • This is the 5th anonymous drop in six months, and the previous four were all claimed by Chinese labs: Zhipu, Xiaomi, Ant, and Meituan Theo Jaffee: " There's no way it's a Flash model. If that's a Flash model, then holy shit, the entire United States is cooked. If that's a Flash model, we need to short the stock market now. Not financial advice."

MTS

376,143 görüntüleme • 5 gün önce