Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

microsoft just released a tool that transcribes a full hour of audio at once, tracking who spoke and when. it's called vibevoice the 7b model processes the full recording in one shot instead of chunking it, so speaker identity and context never break across segments → full speaker diarization... show more

Oliver Prompts

20,947 subscribers

53,501 Aufrufe • vor 2 Monaten •via X (Twitter)

Wissenschaft & Technologie Bildung Nachrichten & Politik

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

🚨 JUST IN: MICROSOFT just open sourced a VOICE AI THAT TRANSCRIBES 60 MINUTES OF AUDIO in a single pass. 100% FREE. It knows who spoke. It knows when they spoke. It knows exactly what they said. All in one shot. No chunking. No context loss. It's called VibeVoice. Not a transcription tool. Not a basic speech to text wrapper. A frontier voice AI family with ASR, TTS, and real time streaming. All open source. All free. Here's what it actually does 👇 VibeVoice ASR - Speech Recognition: → Processes 60 minutes of continuous audio in a single pass → Never slices audio into chunks so global context is never lost → Identifies WHO spoke, WHEN they spoke and WHAT they said simultaneously → Supports customized hotwords for domain specific accuracy → Works in 50+ languages natively → Already adopted by Hugging Face Transformers library → Already being built on by the open source community BY PEOPLE WHO HAD NO IDEA THIS LEVEL OF ACCURACY WAS ALREADY FREE. VibeVoice TTS - Text to Speech: → Generates up to 90 minutes of speech in a single pass → Supports up to 4 distinct speakers in one conversation → Natural turn taking and speaker consistency throughout → Expressive speech that captures emotional nuances → Supports English, Chinese and multiple other languages VibeVoice Realtime - Streaming TTS: → Only 300 millisecond first audible latency → Streams text input in real time → 0.5B parameters so it actually deploys anywhere → Robust long form generation up to 10 minutes → Lightweight enough for production use today The core innovation nobody is talking about: Most voice AI models slice long audio into short chunks. Every time they slice, they lose context. Speaker tracking breaks. Semantic coherence breaks. Accuracy drops. VibeVoice uses continuous speech tokenizers running at an ultra low frame rate of 7.5 Hz. This preserves audio fidelity while dramatically boosting computational efficiency. The entire 60 minutes stays in context. Nothing gets lost. Nobody gets misidentified. The numbers: → VibeVoice ASR 7B - available now on Hugging Face → VibeVoice Realtime 0.5B - try it on Colab right now → 50+ supported languages → 11 distinct English voice styles → 9 multilingual speaker voices → Already integrated into Hugging Face Transformers → Finetuning code now available The wildest part? A voice powered input method called Vibing just built itself on top of VibeVoice ASR. Available on macOS and Windows right now. The open source community is already shipping products on top of this. 100% Open Source. Free to use. Free to fine tune. Free to build on. 🔖 Save this before your competitors find it first. 👇

🚨 JUST IN: MICROSOFT just open sourced a VOICE AI THAT TRANSCRIBES 60 MINUTES OF AUDIO in a single pass. 100% FREE. It knows who spoke. It knows when they spoke. It knows exactly what they said. All in one shot. No chunking. No context loss. It's called VibeVoice. Not a transcription tool. Not a basic speech to text wrapper. A frontier voice AI family with ASR, TTS, and real time streaming. All open source. All free. Here's what it actually does 👇 VibeVoice ASR - Speech Recognition: → Processes 60 minutes of continuous audio in a single pass → Never slices audio into chunks so global context is never lost → Identifies WHO spoke, WHEN they spoke and WHAT they said simultaneously → Supports customized hotwords for domain specific accuracy → Works in 50+ languages natively → Already adopted by Hugging Face Transformers library → Already being built on by the open source community BY PEOPLE WHO HAD NO IDEA THIS LEVEL OF ACCURACY WAS ALREADY FREE. VibeVoice TTS - Text to Speech: → Generates up to 90 minutes of speech in a single pass → Supports up to 4 distinct speakers in one conversation → Natural turn taking and speaker consistency throughout → Expressive speech that captures emotional nuances → Supports English, Chinese and multiple other languages VibeVoice Realtime - Streaming TTS: → Only 300 millisecond first audible latency → Streams text input in real time → 0.5B parameters so it actually deploys anywhere → Robust long form generation up to 10 minutes → Lightweight enough for production use today The core innovation nobody is talking about: Most voice AI models slice long audio into short chunks. Every time they slice, they lose context. Speaker tracking breaks. Semantic coherence breaks. Accuracy drops. VibeVoice uses continuous speech tokenizers running at an ultra low frame rate of 7.5 Hz. This preserves audio fidelity while dramatically boosting computational efficiency. The entire 60 minutes stays in context. Nothing gets lost. Nobody gets misidentified. The numbers: → VibeVoice ASR 7B - available now on Hugging Face → VibeVoice Realtime 0.5B - try it on Colab right now → 50+ supported languages → 11 distinct English voice styles → 9 multilingual speaker voices → Already integrated into Hugging Face Transformers → Finetuning code now available The wildest part? A voice powered input method called Vibing just built itself on top of VibeVoice ASR. Available on macOS and Windows right now. The open source community is already shipping products on top of this. 100% Open Source. Free to use. Free to fine tune. Free to build on. 🔖 Save this before your competitors find it first. 👇

Kanika

221,715 Aufrufe • vor 5 Monaten

Microsoft just killed voice subscriptions. 🤯 They quietly open-sourced VibeVoice, and it’s a total industry disruptor. Transcribe hour-long meetings or generate 90 minutes of natural, multi-speaker speech, all locally on your hardware for free. It handles 50+ languages and complex speaker tracking without the monthly fees. The era of expensive voice apps is officially over. I share updates like these in my free AI community on WhatsApp. Join here

Microsoft just killed voice subscriptions. 🤯 They quietly open-sourced VibeVoice, and it’s a total industry disruptor. Transcribe hour-long meetings or generate 90 minutes of natural, multi-speaker speech, all locally on your hardware for free. It handles 50+ languages and complex speaker tracking without the monthly fees. The era of expensive voice apps is officially over. I share updates like these in my free AI community on WhatsApp. Join here

Vaibhav Sisinty

22,132 Aufrufe • vor 5 Monaten

Microsoft did it again! Speech AI models have a major limitation. They slice long recordings into tiny chunks, lose track of who's speaking, and forget all context halfway through. This is exactly what Microsoft's VibeVoice solves. It's an open-source family of frontier voice AI models for both speech recognition and speech generation. Here's what it can do: > VibeVoice-ASR processes up to 60 minutes of audio in a single pass. No chunking. It outputs structured transcriptions with who spoke, when they spoke, and what they said. > You can feed it custom hotwords like names, technical jargon, or domain-specific terms. The model uses them to significantly improve accuracy on specialized content. > VibeVoice-TTS generates up to 90 minutes of multi-speaker speech with up to 4 distinct speakers. Natural turn-taking, emotional expression, all in one pass. > VibeVoice-Realtime is a 0.5B streaming TTS model with ~300ms first-audio latency. Small enough to deploy practically anywhere. All of this is powered by continuous speech tokenizers running at just 7.5 Hz. This ultra-low frame rate preserves audio quality while making long sequences computationally feasible. I have shared the link to the GitHub repo in the replies!

Microsoft did it again! Speech AI models have a major limitation. They slice long recordings into tiny chunks, lose track of who's speaking, and forget all context halfway through. This is exactly what Microsoft's VibeVoice solves. It's an open-source family of frontier voice AI models for both speech recognition and speech generation. Here's what it can do: > VibeVoice-ASR processes up to 60 minutes of audio in a single pass. No chunking. It outputs structured transcriptions with who spoke, when they spoke, and what they said. > You can feed it custom hotwords like names, technical jargon, or domain-specific terms. The model uses them to significantly improve accuracy on specialized content. > VibeVoice-TTS generates up to 90 minutes of multi-speaker speech with up to 4 distinct speakers. Natural turn-taking, emotional expression, all in one pass. > VibeVoice-Realtime is a 0.5B streaming TTS model with ~300ms first-audio latency. Small enough to deploy practically anywhere. All of this is powered by continuous speech tokenizers running at just 7.5 Hz. This ultra-low frame rate preserves audio quality while making long sequences computationally feasible. I have shared the link to the GitHub repo in the replies!

Akshay 🚀

45,256 Aufrufe • vor 6 Monaten

General Michael Flynn says he’s knows why we’re not getting accountability for the Minnesota daycare fraud He’s looked into Speaker Mike Johnson and he’s getting daycare and healthcare clinic money funneled through PACs Taxpayers are being robbed blind “I want Speaker Johnson to do more. So we started looking at Speaker Johnson's PACs and how many of his PACs turn money back around to daycare and healthcare clinics and that kind of stuff. It's incredible the amounts of money and that's one person, but he happens to be the Speaker of the House. So this is not a partisan thing for me.” There are all in on it.

General Michael Flynn says he’s knows why we’re not getting accountability for the Minnesota daycare fraud He’s looked into Speaker Mike Johnson and he’s getting daycare and healthcare clinic money funneled through PACs Taxpayers are being robbed blind “I want Speaker Johnson to do more. So we started looking at Speaker Johnson's PACs and how many of his PACs turn money back around to daycare and healthcare clinics and that kind of stuff. It's incredible the amounts of money and that's one person, but he happens to be the Speaker of the House. So this is not a partisan thing for me.” There are all in on it.

Wall Street Apes

1,205,507 Aufrufe • vor 8 Monaten

When a motion for the removal of the Speaker is taken up, Article 96 makes it very clear that the Speaker cannot sit in the Chair. The actions of the Speaker also cannot be admitted at that point of time. You (Jagdambika Pal) have been appointed by the Speaker of the Lok Sabha. You are sitting there as a member of the panel of chairpersons appointed by the Speaker of the Lok Sabha. Article 93 states: “The House of the People shall, as soon as may be, choose two members of the House to be respectively Speaker and Deputy Speaker thereof and, so often as the office of the Speaker or Deputy Speaker becomes vacant, the House shall choose another member to be Speaker or Deputy Speaker, as the case may be.” Immediately after the election, the Speaker and Deputy Speaker are supposed to be elected. For the last seven years, you have not elected a Deputy Speaker. You have created a constitutional vacuum. This question is very clear. Article 96 is very clear. 👉The House has to select a person to sit in the Chair. : Congress General Secretary (Org.) K C Venugopal ji in Lok Sabha

When a motion for the removal of the Speaker is taken up, Article 96 makes it very clear that the Speaker cannot sit in the Chair. The actions of the Speaker also cannot be admitted at that point of time. You (Jagdambika Pal) have been appointed by the Speaker of the Lok Sabha. You are sitting there as a member of the panel of chairpersons appointed by the Speaker of the Lok Sabha. Article 93 states: “The House of the People shall, as soon as may be, choose two members of the House to be respectively Speaker and Deputy Speaker thereof and, so often as the office of the Speaker or Deputy Speaker becomes vacant, the House shall choose another member to be Speaker or Deputy Speaker, as the case may be.” Immediately after the election, the Speaker and Deputy Speaker are supposed to be elected. For the last seven years, you have not elected a Deputy Speaker. You have created a constitutional vacuum. This question is very clear. Article 96 is very clear. 👉The House has to select a person to sit in the Chair. : Congress General Secretary (Org.) K C Venugopal ji in Lok Sabha

Congress

112,838 Aufrufe • vor 6 Monaten

Claude Code just shipped v2.1.69 with a new built-in skill: /claude-api It detects your language, picks the right surface (direct API, tool use, or Agent SDK), and loads the relevant reference docs directly into context. Covers streaming, batches, files API, structured outputs, tool use patterns, MCP, also sets model defaults so you're not guessing. Useful when you're building on top of Claude and don't want to context-switch to the docs every 5 minutes.

Claude Code just shipped v2.1.69 with a new built-in skill: /claude-api It detects your language, picks the right surface (direct API, tool use, or Agent SDK), and loads the relevant reference docs directly into context. Covers streaming, batches, files API, structured outputs, tool use patterns, MCP, also sets model defaults so you're not guessing. Useful when you're building on top of Claude and don't want to context-switch to the docs every 5 minutes.

Daniel San

152,831 Aufrufe • vor 6 Monaten

After Effects costs $22.99/month. CapCut Pro costs $9.99/month. A guy named Clement built the free alternative that runs entirely in your browser. It is called Pikimov. Open a competitor's editor and you're locked into a download, an account, and a monthly bill before you touch a single clip. Open Pikimov and you just start. No sign-up, no install, no upload. Load it in Chrome or Edge and you're compositing 4K in seconds, with the editing running locally on your own machine. It packs keyframe animation on nearly every property, particles, motion tracking, rotoscoping, a one-click background remover, transitions, and full 3D model support. Then it goes one step further. It reads After Effects javascript expressions, so the animation code you already know runs straight inside the tab instead of forcing you to relearn anything. Your files never leave your computer. Nothing uploads to a server. Your projects are never fed into AI training, so your privacy isn't the price of admission. No, it does not magically reproduce every plugin and decade-deep feature Adobe bolted onto After Effects. But it breaks the most important rule of the old motion design market: You no longer need a subscription to own the tool.

After Effects costs $22.99/month. CapCut Pro costs $9.99/month. A guy named Clement built the free alternative that runs entirely in your browser. It is called Pikimov. Open a competitor's editor and you're locked into a download, an account, and a monthly bill before you touch a single clip. Open Pikimov and you just start. No sign-up, no install, no upload. Load it in Chrome or Edge and you're compositing 4K in seconds, with the editing running locally on your own machine. It packs keyframe animation on nearly every property, particles, motion tracking, rotoscoping, a one-click background remover, transitions, and full 3D model support. Then it goes one step further. It reads After Effects javascript expressions, so the animation code you already know runs straight inside the tab instead of forcing you to relearn anything. Your files never leave your computer. Nothing uploads to a server. Your projects are never fed into AI training, so your privacy isn't the price of admission. No, it does not magically reproduce every plugin and decade-deep feature Adobe bolted onto After Effects. But it breaks the most important rule of the old motion design market: You no longer need a subscription to own the tool.

Ihtesham Ali

19,708 Aufrufe • vor 23 Tagen

“Nine seconds?!Bonnie blue reveals the wildest reason some guys finish almost instantly.” Speaker 1: How quickly do virgins generally finish? Speaker 2: My shortest video was nine seconds. As soon as he got started, he finished. Speaker 3: I've done that before. I've even finished in my pants. Speaker 2: My favorite was during spring break. I was dancing on stage with a guy, and he finished almost immediately. Speaker 3: You have the Thanos hand—you can just make it happen. Speaker 2: Not always. Sometimes they're too nervous, or they've done something beforehand. Speaker 1: Are you annoyed when they can't finish? Speaker 2: No, but it gets exhausting. I'm running out of options and getting tired. Speaker 1: An hour and a half in? Speaker 2: Yeah. I'm like, "Whew..."

Sensitive content

“Nine seconds?!Bonnie blue reveals the wildest reason some guys finish almost instantly.” Speaker 1: How quickly do virgins generally finish? Speaker 2: My shortest video was nine seconds. As soon as he got started, he finished. Speaker 3: I've done that before. I've even finished in my pants. Speaker 2: My favorite was during spring break. I was dancing on stage with a guy, and he finished almost immediately. Speaker 3: You have the Thanos hand—you can just make it happen. Speaker 2: Not always. Sometimes they're too nervous, or they've done something beforehand. Speaker 1: Are you annoyed when they can't finish? Speaker 2: No, but it gets exhausting. I'm running out of options and getting tired. Speaker 1: An hour and a half in? Speaker 2: Yeah. I'm like, "Whew..."

osaze

643,461 Aufrufe • vor 29 Tagen

Seven years too late, but it's great to see the issue of 'missing' Deputy Speaker in #LokSabha finally being debated in House! As MP Mohd. Jawed moved the resolution to remove Om Birla as Speaker of #LokSabha, MP Asaduddin Owaisi (Asaduddin Owaisi) raises a very fundamental point - when such a motion has been moved against the Speaker, who has the authority to preside? There is no Deputy Speaker in House & no sense of the House was taken to determine if Jagdambika Pal (who is in the Chair) can preside in terms of Article 95(2) (see video) MP Nishikant Dubey interprets Article 95(2) to say that House has determined as per rules and procedure that Jagdambika Pal. Then, Parliamentary Affairs Minister Kiren Rijiju jumps in and says that the point is unnecessary, already a ruling has been given. However, it can be argued that Article 95(2) should have no application here, because it talks about Speaker and Deputy Speaker being 'absent'. Article 95(1) is the appropriate Article to be invoked here which talks about 'vacancy' in office of Speaker and Deputy Speaker. A combined reading of both 95(1) and 95(2) - Speaker is absent but post of Deputy Speaker is vacant - so who should preside? Contd..

Seven years too late, but it's great to see the issue of 'missing' Deputy Speaker in #LokSabha finally being debated in House! As MP Mohd. Jawed moved the resolution to remove Om Birla as Speaker of #LokSabha, MP Asaduddin Owaisi (Asaduddin Owaisi) raises a very fundamental point - when such a motion has been moved against the Speaker, who has the authority to preside? There is no Deputy Speaker in House & no sense of the House was taken to determine if Jagdambika Pal (who is in the Chair) can preside in terms of Article 95(2) (see video) MP Nishikant Dubey interprets Article 95(2) to say that House has determined as per rules and procedure that Jagdambika Pal. Then, Parliamentary Affairs Minister Kiren Rijiju jumps in and says that the point is unnecessary, already a ruling has been given. However, it can be argued that Article 95(2) should have no application here, because it talks about Speaker and Deputy Speaker being 'absent'. Article 95(1) is the appropriate Article to be invoked here which talks about 'vacancy' in office of Speaker and Deputy Speaker. A combined reading of both 95(1) and 95(2) - Speaker is absent but post of Deputy Speaker is vacant - so who should preside? Contd..

Maadhyam

23,030 Aufrufe • vor 6 Monaten

.Speaker Mike Johnson: "The Democrats had every one of the Epstein files in their possession for the four long years of the Biden Administration... and not a single one of the people who are so loud and animated right now—they never said anything about it for all those four years."

.Speaker Mike Johnson: "The Democrats had every one of the Epstein files in their possession for the four long years of the Biden Administration... and not a single one of the people who are so loud and animated right now—they never said anything about it for all those four years."

Rapid Response 47

235,983 Aufrufe • vor 10 Monaten

Introducing Diarization Bench, Voice Arena's benchmark for who spoke when. The metric we measure is diarization error rate, or DER. It measures how much of a conversation a model attaches to the wrong person. Every second it misses, invents, or gives to another speaker counts against it. Here's what we did. 139 conversations recorded for this board, in rooms and on calls, with people interrupting each other throughout. 12 systems scored under a single goal: testing models in the real-world conditions they are actually deployed in. NVIDIA's Nemotron 3 leads at 14.72%. 🧵

Introducing Diarization Bench, Voice Arena's benchmark for who spoke when. The metric we measure is diarization error rate, or DER. It measures how much of a conversation a model attaches to the wrong person. Every second it misses, invents, or gives to another speaker counts against it. Here's what we did. 139 conversations recorded for this board, in rooms and on calls, with people interrupting each other throughout. 12 systems scored under a single goal: testing models in the real-world conditions they are actually deployed in. NVIDIA's Nemotron 3 leads at 14.72%. 🧵

Shobhit Banga

629,621 Aufrufe • vor 2 Tagen

🎉 Congrats to MOSI + OpenMOSS on the release of MOSS-Transcribe-Diarize-0.9B — a genuinely impressive end-to-end ASR model for real-world, multi-speaker conversations. We're proud to partner with them for day-0 support on mlx-audio (Python & Swift). Now running local-first on Apple Silicon: 🎙️ transcript + speaker labels + timestamps in one pass 🗣️ unlimited-speaker diarization ⏱️ up to ~90 min of audio per input 🌍 90+ languages 🧠 128K context • Whisper-Medium encoder + Qwen3-0.6B decoder 🎯 hotword boosting for names, products & domain terms Perfect for meetings, podcasts, interviews, and long-form call analysis — no cloud, no data leaving your Mac. Get started now: 🐍 Python > uv pip install -U mlx-audio 🍎 Swift .package(url: " from: "0.1.3") Go build. 🚀

🎉 Congrats to MOSI + OpenMOSS on the release of MOSS-Transcribe-Diarize-0.9B — a genuinely impressive end-to-end ASR model for real-world, multi-speaker conversations. We're proud to partner with them for day-0 support on mlx-audio (Python & Swift). Now running local-first on Apple Silicon: 🎙️ transcript + speaker labels + timestamps in one pass 🗣️ unlimited-speaker diarization ⏱️ up to ~90 min of audio per input 🌍 90+ languages 🧠 128K context • Whisper-Medium encoder + Qwen3-0.6B decoder 🎯 hotword boosting for names, products & domain terms Perfect for meetings, podcasts, interviews, and long-form call analysis — no cloud, no data leaving your Mac. Get started now: 🐍 Python > uv pip install -U mlx-audio 🍎 Swift .package(url: " from: "0.1.3") Go build. 🚀

Prince Canuma

11,639 Aufrufe • vor 2 Monaten

“During a live debate, a Sikh speaker openly spoke his truth, stating that he does not bow his head in temples and does not believe in Hindu gods. He said this clearly in front of the so-called Gaggu Pandit. See and hear it for yourself with your own eyes.”

“During a live debate, a Sikh speaker openly spoke his truth, stating that he does not bow his head in temples and does not believe in Hindu gods. He said this clearly in front of the so-called Gaggu Pandit. See and hear it for yourself with your own eyes.”

𝕄𝔾™

94,099 Aufrufe • vor 9 Monaten

BREAKING: President Biden just explicitly called out Speaker Mike Johnson on the Ukraine Funding bill. "Early this morning, the United States Senate voted overwhelmingly by a margin of 70-29 to move forward with the bipartisan national security bill. Now it moves to the House, and I urge Speaker Johnson to bring it to the floor immediately. There is no question that if the Senate bill is put to a vote in the House of Representatives, it would pass. So I call on the Speaker to let the full House speak its mind and not allow a minority of the most extreme voices in the House to block this bill from even being voted on." Shouldn't the House vote? Isn't that what Democracy is about?

BREAKING: President Biden just explicitly called out Speaker Mike Johnson on the Ukraine Funding bill. "Early this morning, the United States Senate voted overwhelmingly by a margin of 70-29 to move forward with the bipartisan national security bill. Now it moves to the House, and I urge Speaker Johnson to bring it to the floor immediately. There is no question that if the Senate bill is put to a vote in the House of Representatives, it would pass. So I call on the Speaker to let the full House speak its mind and not allow a minority of the most extreme voices in the House to block this bill from even being voted on." Shouldn't the House vote? Isn't that what Democracy is about?

Ed Krassenstein

1,253,160 Aufrufe • vor 2 Jahren

NVIDIA just removed one of the biggest friction points in Voice AI. PersonaPlex-7B is an open-source, full-duplex conversational model. Free, open source (MIT), with open model weights on Hugging Face 🤗 Links to repo and weights in 🧵↓ The traditional ASR → LLM → TTS pipeline forces rigid turn-taking. It’s efficient, but it never feels natural. PersonaPlex-7B changes that. This NVIDIA model can listen and speak at the same time. It runs directly on continuous audio tokens with a dual-stream transformer, generating text and audio in parallel instead of passing control between components. That unlocks: → instant back-channel responses → interruptions that feel human → real conversational rhythm Persona control is fully zero-shot! If you’re building low-latency assistants or support agents, this is a big step forward 🔥

NVIDIA just removed one of the biggest friction points in Voice AI. PersonaPlex-7B is an open-source, full-duplex conversational model. Free, open source (MIT), with open model weights on Hugging Face 🤗 Links to repo and weights in 🧵↓ The traditional ASR → LLM → TTS pipeline forces rigid turn-taking. It’s efficient, but it never feels natural. PersonaPlex-7B changes that. This NVIDIA model can listen and speak at the same time. It runs directly on continuous audio tokens with a dual-stream transformer, generating text and audio in parallel instead of passing control between components. That unlocks: → instant back-channel responses → interruptions that feel human → real conversational rhythm Persona control is fully zero-shot! If you’re building low-latency assistants or support agents, this is a big step forward 🔥

Charly Wargnier ♨️

566,178 Aufrufe • vor 8 Monaten

THIS GUY STACKED MAC MINIS TO RUN AI LOCALLY AND IT CODES FOR FREE no API. no subscription. no cloud. what he's running: - EXO across multiple Mac Minis - Qwen 2.5 Coder 7B locally - Zed editor connected to the model - GPU usage visible in real time the math: - Mac Mini M4: $599 one-time - electricity: $3/month - API costs: $0 vs $459/month in subscriptions if you want Claude Code to run at this level ClaudeKit gives it the structure to do that ( full breakdown in the article below

THIS GUY STACKED MAC MINIS TO RUN AI LOCALLY AND IT CODES FOR FREE no API. no subscription. no cloud. what he's running: - EXO across multiple Mac Minis - Qwen 2.5 Coder 7B locally - Zed editor connected to the model - GPU usage visible in real time the math: - Mac Mini M4: $599 one-time - electricity: $3/month - API costs: $0 vs $459/month in subscriptions if you want Claude Code to run at this level ClaudeKit gives it the structure to do that ( full breakdown in the article below

Madni Aghadi

26,421 Aufrufe • vor 3 Monaten

🚨FOUR YEARS OF SILENCE, NOW SUDDEN FURY🚨 Speaker Mike Johnson: "The Democrats had every one of the Epstein files in their possession for the four long years of the Biden Administration... and not a single one of the people who are so loud and animated right now—they never said anything about it for all those four years."

🚨FOUR YEARS OF SILENCE, NOW SUDDEN FURY🚨 Speaker Mike Johnson: "The Democrats had every one of the Epstein files in their possession for the four long years of the Biden Administration... and not a single one of the people who are so loud and animated right now—they never said anything about it for all those four years."

Laura Ingraham

207,495 Aufrufe • vor 10 Monaten