ModelOS

@p1oezxsA4iyP1le All in due time. We will also open a discord

@ModelosMDL Where is the mining pool address?

Running the very last test now, making sure inference works end to end. We're not launching half-baked. When we go live, it's all there: 🔹 Merge-mined with Pearl 🔹 Our pool, paying both $PRL and $MDL 🔹 Inference live with the DeepSeek models, more added after 🔹 Every inference tx verifiable on-chain 🔹 OTC live, so you can trade $MDL from day one We know you're impatient. Hang with us, we're almost there. Nobody's going to regret the wait. You're early. 🔔

@cryptic_idx blablabla ❤️

@ModelosMDL just send me docs , dont blablabla

Btw we don't actually think our AI is dumb. It's a very nice AI. Very smart. We're proud of it 🙃

@Al_manation soon 🙃 We are building the first real onchain model POW chain, bear with us

@ModelosMDL You are about to enter the third week of stealth launch soon. Stealth launch wen?

Get ready. Stealth launch is coming. We're wrapping up the final testing now, making sure everything runs clean. Once it's solid, it's go time. Have your GPU rigs ready. 🔔

@ronanblaxke Not yet doing the last testing

@ModelosMDL is it live yet?

But who actually buys the inference? You do, anyone can. At launch there's a chat interface and an API where you request inference from miners and pay in $MDL straight from your wallet. Over time it grows into a full decentralized inference marketplace. And soon you'll be able to host any model, the DeepSeek R1 distills, Kimi K2, GLM 4.5, our own distilled model, and more. Miners serve it. Anyone can use it.

@Hexo_nem That's the idea!

@ModelosMDL Powerful idea, simple access for everyone

@YGYxop6 In the next few days.

@ModelosMDL 有没有一个大概时间呢

@y52f27npck Very soon

@ModelosMDL When are we getting going on this? I am so keen to move my rigs to this!!

How inference works on ModelOS: Your GPU isn't just mining, it's serving real AI. Miners run a vLLM miner, and the proof-of-work is the inference itself. Every block is a genuine model run. At launch you can serve: DeepSeek R1 distills (70B, 32B, 14B, 7B), plus Kimi K2, GLM 4.5, and our own distilled model. Mine blocks, serve inference, and keep earning the $PRL you're already mining. One GPU, three ways to earn.

@yexd17 Both 4090 and H100 will work. We will support all rtx only sm70 and below not accepted

@ModelosMDL What are the weights for each model? What's the best graphics card? A 4090 or an H100?

@robono75168 Soon. We will announce when ready and launched

@ModelosMDL 下载地址？官方网站？

@Web3Torch no

@ModelosMDL pool.modeloslab.xyz Is this good

@YGYxop6 When everything is ready. We are not rushing this with a half ready product.

@ModelosMDL 什么时候上线？ 我已经等了两天了～

@ModelosMDL Is there going to be an inference marketplace for those that want to buy inference from miners?

@anibalbosco Yes. At launch it's a chat interface and an API, you request inference from miners and pay in $MDL. Over time it will grow into a full decentralized inference marketplace.

@0xFelix1989 We modified the vllm

@ModelosMDL 你们是工程化改造了vllm么？还是对这些模型另行通知全面的pearl适配？把插件hook插入了FNN层？？太佩服你们的技术能力了！！！

@DaLan13193 Soon

@ModelosMDL when start?