正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Score Studio does both. Native local inference, compute & storage. Native integrations with Chutes engy.ai Good Morning lium.io Hippius. Local + Decentralized. Done.

Score - Subnet 44

9,298 subscribers

13,188 次观看 • 16 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Introducing Enterprise NAS, built on ZFS. Completely private, local enterprise storage — without the enterprise tax. 🔹 Neoverse N2 Compute 🔹 64GB ECC Memory 🔹 Native ZFS & iSCSI 🔹 Dual 25GbE Networking 🔹 Redundant Power

Introducing Enterprise NAS, built on ZFS. Completely private, local enterprise storage — without the enterprise tax. 🔹 Neoverse N2 Compute 🔹 64GB ECC Memory 🔹 Native ZFS & iSCSI 🔹 Dual 25GbE Networking 🔹 Redundant Power

Ubiquiti Inc

332,327 次观看 • 2 个月前

1/3 We’re excited to back @Irysxyz - the datachain that fuses high-speed decentralized storage with native smart contract execution. With 100,000 data tx/sec, fixed pricing, and compute built in, Irys redefines what’s possible at the intersection of crypto, AI, and data.

1/3 We’re excited to back @Irysxyz - the datachain that fuses high-speed decentralized storage with native smart contract execution. With 100,000 data tx/sec, fixed pricing, and compute built in, Irys redefines what’s possible at the intersection of crypto, AI, and data.

Breed

16,875 次观看 • 1 年前

A decentralized AI compute play just outran 99% of the crypto market this month $AKT, the native token of Akash Network, is up 72% on the month and leading CoinMarketCap's Broad Market category despite a 12% pullback Saturday testing $0.595 support. The DePIN GPU marketplace lets users rent NVIDIA H100s for $1.49/hour vs $43K outright. Founder Greg Osuri presented at the Economist Impact AI Compute Summit in Amsterdam this week. Recent integrations with Venice ai and FLock io target decentralized AI inference, the same vertical NEAR and Sahara AI are also rotating into.

A decentralized AI compute play just outran 99% of the crypto market this month $AKT, the native token of Akash Network, is up 72% on the month and leading CoinMarketCap's Broad Market category despite a 12% pullback Saturday testing $0.595 support. The DePIN GPU marketplace lets users rent NVIDIA H100s for $1.49/hour vs $43K outright. Founder Greg Osuri presented at the Economist Impact AI Compute Summit in Amsterdam this week. Recent integrations with Venice ai and FLock io target decentralized AI inference, the same vertical NEAR and Sahara AI are also rotating into.

BSCN

10,984 次观看 • 3 个月前

datadog for humans - realtime heart rate - correlates with typing speed, clicks, pointer travel distance & what app you're in - breakdowns by websites & slack channels - insights in deep focus, context switching, hr per-app - local, native app

datadog for humans - realtime heart rate - correlates with typing speed, clicks, pointer travel distance & what app you're in - breakdowns by websites & slack channels - insights in deep focus, context switching, hr per-app - local, native app

JohnPhamous

131,421 次观看 • 7 个月前

local LLMs on Mac are getting good. but the workflow around models is still messy. you have models in: •⁠ ⁠LM Studio •⁠ ⁠Ollama •⁠ ⁠Hugging Face cache •⁠ ⁠random folders •⁠ ⁠manual downloads and every runtime expects something slightly different. we built ModelHub to clean up this layer. it’s a native macOS menu bar app for discovering, downloading, and managing local LLMs. not a replacement for Ollama, oMLX or LM Studio. it sits beside them. Ollama = run models MLX = Apple Silicon acceleration LM Studio = local model workspace Hugging Face = model ecosystem ModelHub = model discovery + management layer we’re live on Product Hunt today. would love feedback from people running local models on Mac.

local LLMs on Mac are getting good. but the workflow around models is still messy. you have models in: •⁠ ⁠LM Studio •⁠ ⁠Ollama •⁠ ⁠Hugging Face cache •⁠ ⁠random folders •⁠ ⁠manual downloads and every runtime expects something slightly different. we built ModelHub to clean up this layer. it’s a native macOS menu bar app for discovering, downloading, and managing local LLMs. not a replacement for Ollama, oMLX or LM Studio. it sits beside them. Ollama = run models MLX = Apple Silicon acceleration LM Studio = local model workspace Hugging Face = model ecosystem ModelHub = model discovery + management layer we’re live on Product Hunt today. would love feedback from people running local models on Mac.

sabesh 📟

31,497 次观看 • 3 个月前

Good Morning! ☕️ Excited about Planck 🙌 – the world's first AI Layer 0 blockchain! Powering decentralized AI chains with native GPU access, sovereign agents, and DePINs at scale. Backed by USDT co-founder, just raised $200M commitment. The future of AI + Web3 is here. Check it out: #DeAI #Blockchain #partner #AI #Depin Official TG: Official Discord:

Good Morning! ☕️ Excited about Planck 🙌 – the world's first AI Layer 0 blockchain! Powering decentralized AI chains with native GPU access, sovereign agents, and DePINs at scale. Backed by USDT co-founder, just raised $200M commitment. The future of AI + Web3 is here. Check it out: #DeAI #Blockchain #partner #AI #Depin Official TG: Official Discord:

Dapp Centre

34,133 次观看 • 11 个月前

Manoj Yadav from Jharkhand with his friends residing at Maraimalai Nagar had claimed in a video that they were beaten up by local Tamil and were facing problems in their work place, They'd requested the Govt of Tamilnadu & Jharkhand to help them to return back to their native.

Manoj Yadav from Jharkhand with his friends residing at Maraimalai Nagar had claimed in a video that they were beaten up by local Tamil and were facing problems in their work place, They'd requested the Govt of Tamilnadu & Jharkhand to help them to return back to their native.

Mohammed Zubair

435,687 次观看 • 3 年前

Our OSS engineer Clelia Bertelli (🦀/acc) recently built 𝗹𝗶𝘁𝗲𝘀𝗲𝗮𝗿𝗰𝗵, a fully local document ingestion and retrieval CLI/TUI application powered by LiteParse ⚡ litesearch demonstrates how developers can assemble a high-performance, local-first retrieval pipeline using open tools from across the ecosystem: • Parsing: LiteParse, the fast and accurate document parser we recently open sourced • Chunking: @ChonkieAI • Embeddings: A local Nomic model via Hugging Face transformers.js • Vector storage: A local Qdrant edge shard (custom-built in Rust and compiled as a native add-on) • Retrieval: Query stored files with optional path-based filtering and configurable relevance thresholds • Runtime: Bun for speed and versatility 💻 Check out the repository and try it yourself: 📚 LiteParse docs:

Our OSS engineer Clelia Bertelli (🦀/acc) recently built 𝗹𝗶𝘁𝗲𝘀𝗲𝗮𝗿𝗰𝗵, a fully local document ingestion and retrieval CLI/TUI application powered by LiteParse ⚡ litesearch demonstrates how developers can assemble a high-performance, local-first retrieval pipeline using open tools from across the ecosystem: • Parsing: LiteParse, the fast and accurate document parser we recently open sourced • Chunking: @ChonkieAI • Embeddings: A local Nomic model via Hugging Face transformers.js • Vector storage: A local Qdrant edge shard (custom-built in Rust and compiled as a native add-on) • Retrieval: Query stored files with optional path-based filtering and configurable relevance thresholds • Runtime: Bun for speed and versatility 💻 Check out the repository and try it yourself: 📚 LiteParse docs:

LlamaIndex 🦙

14,900 次观看 • 5 个月前

attn. people who want an actually smart TV– stable version of GoatRemote is out added cloud model support for older macs. should now work on base M1 macs perfectly, which struggled with local models absurdly fast w/ Groq Inc inference for both Whisper & LLM (Kimi K2), see video

attn. people who want an actually smart TV– stable version of GoatRemote is out added cloud model support for older macs. should now work on base M1 macs perfectly, which struggled with local models absurdly fast w/ Groq Inc inference for both Whisper & LLM (Kimi K2), see video

murat 🍥

323,500 次观看 • 9 个月前

GLM-5.2 running on Mac Studio Clusters or RTX GPU rigs isn't how Local AI will get mass adopted. For mass adoption we need to focus on two axes: 1. Intelligence/Speed Frontier. This is being tracked on local dot ai. Aggressive co-design is needed across the entire stack to push up the frontier specifically for local hardware. Better kernels, inference tricks like spec decoding, quantizing models, model routing. 2. Usability / UX. To use Local AI today, you need to install CLIs, select a model, a quantization, a harness that works best with that model, and you need to configure your inference engine. It's not very accessible. More work needs to be done on making this seamless, so the user doesn't even know the AI is running locally.

GLM-5.2 running on Mac Studio Clusters or RTX GPU rigs isn't how Local AI will get mass adopted. For mass adoption we need to focus on two axes: 1. Intelligence/Speed Frontier. This is being tracked on local dot ai. Aggressive co-design is needed across the entire stack to push up the frontier specifically for local hardware. Better kernels, inference tricks like spec decoding, quantizing models, model routing. 2. Usability / UX. To use Local AI today, you need to install CLIs, select a model, a quantization, a harness that works best with that model, and you need to configure your inference engine. It's not very accessible. More work needs to be done on making this seamless, so the user doesn't even know the AI is running locally.

Alex Cheema

30,820 次观看 • 1 个月前

Good morning, Krewe! Come celebrate International Women’s Day & support local with more than 50 female-owned businesses, live music, fitness classes and more on-site. Open to everyone from 10-3! See you soon!

Good morning, Krewe! Come celebrate International Women’s Day & support local with more than 50 female-owned businesses, live music, fitness classes and more on-site. Open to everyone from 10-3! See you soon!

Tampa Bay Buccaneers

59,049 次观看 • 1 年前

I'm excited to introduce GeoLibre, a lightweight, cloud-native desktop GIS built with MapLibre GL JS and Tauri. GeoLibre is designed for modern geospatial workflows, combining the flexibility of web technologies with the performance of a native desktop application. The current prototype includes a MapLibre-powered map workspace, local vector data import, project persistence, and built-in plugins for basemaps, layer control, swipe, street view, lidar, GeoAgent, and GeoEditor integrations. GeoLibre can run directly in a web browser or as a standalone cross-platform desktop application (<30 MB). GitHub: Website: Live demo: Feedback, ideas, and contributions are welcome. #GeoLibre #GIS #Geospatial #MapLibre #OpenSource #CloudNative

I'm excited to introduce GeoLibre, a lightweight, cloud-native desktop GIS built with MapLibre GL JS and Tauri. GeoLibre is designed for modern geospatial workflows, combining the flexibility of web technologies with the performance of a native desktop application. The current prototype includes a MapLibre-powered map workspace, local vector data import, project persistence, and built-in plugins for basemaps, layer control, swipe, street view, lidar, GeoAgent, and GeoEditor integrations. GeoLibre can run directly in a web browser or as a standalone cross-platform desktop application (<30 MB). GitHub: Website: Live demo: Feedback, ideas, and contributions are welcome. #GeoLibre #GIS #Geospatial #MapLibre #OpenSource #CloudNative

Qiusheng Wu

34,744 次观看 • 3 个月前

Mother of sl@*n daughter gets on a Live & does this. R'Mani,5, & her father Ronnie Smith, 30, whose rapper name was G$ Lil Ronnie, were k*IIed at a local car wash on March 3rd. Both suspects are now in custody and both are being charged with Capital Mů*dër Of Multiple Persons.

Mother of sl@n daughter gets on a Live & does this. R'Mani,5, & her father Ronnie Smith, 30, whose rapper name was G$ Lil Ronnie, were kIIed at a local car wash on March 3rd. Both suspects are now in custody and both are being charged with Capital Mů*dër Of Multiple Persons.

Southern FFA Family

26,520 次观看 • 1 年前

>build a 1.5B VLA on top of MiniCPM-V 4.6 >compete with π0.5 and Qwen-VLA >use roughly half the visual-processing compute >remember previous steps without blowing up inference cost >pull the network plug >let the robot keep tracking — fully local, fully onboard >with CUDA Graph optimization and custom Triton fused kernels, MiniCPM-Robot inference throughput goes from 10 Hz → 33 Hz, and up to 36 Hz on the same NVIDIA H20 >release the models and framework as open source so why does robotics still rely on bigger models and the cloud? OpenBMB just dropped MiniCPM-Robot at WAIC two models + one inference framework 🧵

>build a 1.5B VLA on top of MiniCPM-V 4.6 >compete with π0.5 and Qwen-VLA >use roughly half the visual-processing compute >remember previous steps without blowing up inference cost >pull the network plug >let the robot keep tracking — fully local, fully onboard >with CUDA Graph optimization and custom Triton fused kernels, MiniCPM-Robot inference throughput goes from 10 Hz → 33 Hz, and up to 36 Hz on the same NVIDIA H20 >release the models and framework as open source so why does robotics still rely on bigger models and the cloud? OpenBMB just dropped MiniCPM-Robot at WAIC two models + one inference framework 🧵

arc.

48,279 次观看 • 1 个月前

OK this is actually very good Manus “my computer” can interact with your own local folders So you can basically use it to: - Create a second brain w/ your docs (01:05) - Sort even thousands of files (03:04) - Build any web or native app (06:26) And even add your own skills (see the video) Compatible with macOS and Windows from day one.

OK this is actually very good Manus “my computer” can interact with your own local folders So you can basically use it to: - Create a second brain w/ your docs (01:05) - Sort even thousands of files (03:04) - Build any web or native app (06:26) And even add your own skills (see the video) Compatible with macOS and Windows from day one.

Paul Couvert

16,953 次观看 • 5 个月前

The industry's safest bridge now lets you bridge more native tokens to avoid wrapped token risks. Our friends at Wanchain have done it again. They already have the best bridge in the industry and with XFlows you can bridge native USDT, USDC, BTC, or ETH seamlessly. And now this includes other native chain tokens like BNB, POL, or Solana. Plus, XFlows is now its own standalone app. This makes integrations with other apps you already use and DEX aggregators even easier. It's a win/win/win. ✅Users get more access to better safer bridging ✅Apps get more access and can offer bridging with XFlows, and ✅Wanchain users and $WAN holders should make $$ too. It's a good time to get some $WAN. Congrats to Wanchain. Here is our video on the new standalone app launch of XFlows.

The industry's safest bridge now lets you bridge more native tokens to avoid wrapped token risks. Our friends at Wanchain have done it again. They already have the best bridge in the industry and with XFlows you can bridge native USDT, USDC, BTC, or ETH seamlessly. And now this includes other native chain tokens like BNB, POL, or Solana. Plus, XFlows is now its own standalone app. This makes integrations with other apps you already use and DEX aggregators even easier. It's a win/win/win. ✅Users get more access to better safer bridging ✅Apps get more access and can offer bridging with XFlows, and ✅Wanchain users and $WAN holders should make $$ too. It's a good time to get some $WAN. Congrats to Wanchain. Here is our video on the new standalone app launch of XFlows.

Altcoin Buzz

22,744 次观看 • 1 年前

How does Blum build in APAC? 👀 Online, offline – we’re everywhere. Local TGs? Got ‘em. Korea, Japan, Vietnam, Indonesia – all in native languages, all with top-tier mods keeping the signal strong. ✨ APAC is also a hotspot for IRL crypto action. If you’re in Hong Kong next week, pull up. Might be some surprises waiting. 🎥 Don’t miss the latest highlights from Blum Chats!

How does Blum build in APAC? 👀 Online, offline – we’re everywhere. Local TGs? Got ‘em. Korea, Japan, Vietnam, Indonesia – all in native languages, all with top-tier mods keeping the signal strong. ✨ APAC is also a hotspot for IRL crypto action. If you’re in Hong Kong next week, pull up. Might be some surprises waiting. 🎥 Don’t miss the latest highlights from Blum Chats!

Blum

53,350 次观看 • 1 年前

Everyone condemns the assault of the black girl Thomas Knyvett College in Ashford. Meanwhile I assume this disgusting assault from Oldham will be investigated with equal vigour by Good Morning Britain & Daniel Henry, command Parliamentary time by Janet Daby MP &the condemnation of the local MP.

Everyone condemns the assault of the black girl Thomas Knyvett College in Ashford. Meanwhile I assume this disgusting assault from Oldham will be investigated with equal vigour by Good Morning Britain & Daniel Henry, command Parliamentary time by Janet Daby MP &the condemnation of the local MP.

David Atherton

1,228,980 次观看 • 3 年前