Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

A DEVELOPER ASKED LOCAL AI TO SPIN UP 64 AGENTS IN PARALLEL. IT RAN FOR 8 HOURS WITHOUT ASKING PERMISSION AND WITHOUT A SINGLE API CALL. Gemma 4 refused. Qwen 3.6 said nothing and started working. Zero bills. The model didn't negotiate, it just built.

0xMarioNawfal

252,905 subscribers

61,845 просмотров • 2 месяцев назад •via X (Twitter)

Юмор Новости и политика Наука и технологии

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Claude Code is now completely free forever 🤯 Just connect it to Ollama and run a local model like Google’s new Gemma 4. That means Claude Code agents can run directly on your computer with zero API bills and zero subscriptions. Google may have just ended AI subscription fees for good. 🚀

Claude Code is now completely free forever 🤯 Just connect it to Ollama and run a local model like Google’s new Gemma 4. That means Claude Code agents can run directly on your computer with zero API bills and zero subscriptions. Google may have just ended AI subscription fees for good. 🚀

Julian Goldie SEO

10,098 просмотров • 4 месяцев назад

HERMES CAN NOW RUN FOR FREE FOREVER A new Gemma 4 update just removed the biggest problem with local AI agents. The Upgrade: → Gemma 4 runs around 90% faster on Apple Silicon using Ollama + MLX → Plug it into Hermes with a few terminal commands → Run private agent workflows without subscriptions, token limits, or API bills What It Can Actually Do: ✓ Build and preview apps locally ✓ Use /learn to turn tutorials into permanent skills ✓ Read files, analyse landing pages, summarise emails, and track AI news ✓ Run loops until a task is complete instead of waiting for another prompt ✓ Launch multiple Gemma 4 subagents to work on separate tasks in parallel No Apple Silicon? ✔ OpenRouter offers the 31B model through a free API The real win is not faster chat. It is having Hermes build, retry, check its work, and operate in the background without charging you for every loop.

HERMES CAN NOW RUN FOR FREE FOREVER A new Gemma 4 update just removed the biggest problem with local AI agents. The Upgrade: → Gemma 4 runs around 90% faster on Apple Silicon using Ollama + MLX → Plug it into Hermes with a few terminal commands → Run private agent workflows without subscriptions, token limits, or API bills What It Can Actually Do: ✓ Build and preview apps locally ✓ Use /learn to turn tutorials into permanent skills ✓ Read files, analyse landing pages, summarise emails, and track AI news ✓ Run loops until a task is complete instead of waiting for another prompt ✓ Launch multiple Gemma 4 subagents to work on separate tasks in parallel No Apple Silicon? ✔ OpenRouter offers the 31B model through a free API The real win is not faster chat. It is having Hermes build, retry, check its work, and operate in the background without charging you for every loop.

Julian Goldie SEO

11,234 просмотров • 1 месяц назад

GOOGLE JUST GAVE AI AGENTS A FREE LOCAL BRAIN * Gemma 4 can run locally through Ollama and plug directly into agent frameworks like Hermes and OpenClaw * Developers get private, offline AI for coding, content creation, and automation without recurring API costs

GOOGLE JUST GAVE AI AGENTS A FREE LOCAL BRAIN * Gemma 4 can run locally through Ollama and plug directly into agent frameworks like Hermes and OpenClaw * Developers get private, offline AI for coding, content creation, and automation without recurring API costs

0xMarioNawfal

52,332 просмотров • 2 месяцев назад

Claude Code is now completely free forever 🤯 Google just dropped Gemma 4 on Ollama, which means you can run Claude Code locally with zero API bills and zero subscriptions. Just install Gemma 4, connect it to Claude Code, and suddenly you have free AI agents running directly on your computer. Google may have just killed AI subscription costs. 🚀

Claude Code is now completely free forever 🤯 Google just dropped Gemma 4 on Ollama, which means you can run Claude Code locally with zero API bills and zero subscriptions. Just install Gemma 4, connect it to Claude Code, and suddenly you have free AI agents running directly on your computer. Google may have just killed AI subscription costs. 🚀

Julian Goldie SEO

607,249 просмотров • 4 месяцев назад

The 12 Hours. At a time when the word "car" didn't even exist, and horses still powered the world, one woman chose belief over convention. To prove that her husband's invention could change mobility forever. Bertha Benz set out on the world's first long-distance automobile journey without permission, without roads, and without certainty, it took 12 hours and she made it. She faced breakdowns, scepticism, and countless obstacles, yet refused to stop. That single journey didn't just prove a machine worked, it changed how the world would move forever.

The 12 Hours. At a time when the word "car" didn't even exist, and horses still powered the world, one woman chose belief over convention. To prove that her husband's invention could change mobility forever. Bertha Benz set out on the world's first long-distance automobile journey without permission, without roads, and without certainty, it took 12 hours and she made it. She faced breakdowns, scepticism, and countless obstacles, yet refused to stop. That single journey didn't just prove a machine worked, it changed how the world would move forever.

Brian Roemmele

96,386 просмотров • 7 месяцев назад

I tested Gemma 4 12b on my Macbook Pro M5 Max with 128GB of unified memory. It runs VERY slow for a 12b parameter model. 44 tokens/second. The lava lamp that it produced was also terrible. I would stick to Qwen 3.6 27b or Qwen 3.6 35b. Google is still way behind, even with their local models.

I tested Gemma 4 12b on my Macbook Pro M5 Max with 128GB of unified memory. It runs VERY slow for a 12b parameter model. 44 tokens/second. The lava lamp that it produced was also terrible. I would stick to Qwen 3.6 27b or Qwen 3.6 35b. Google is still way behind, even with their local models.

BridgeMind

70,559 просмотров • 2 месяцев назад

Pi agent is the Arch Linux of coding agents Qwen 3.6 Plus not caching? > No problem. Just ask Pi to patch itself from a community fork Kimi K2.6 imploding mid reasoning? > No problem. Just pull a snippet from a good Samaritan and let Pi test it on itself Now, I can use the reliable Qwen 3.6 Plus without busting my OpenCode Go sub, and the capable Kimi K2.6 without 404s The beauty of Pi is it can customize itself

Pi agent is the Arch Linux of coding agents Qwen 3.6 Plus not caching? > No problem. Just ask Pi to patch itself from a community fork Kimi K2.6 imploding mid reasoning? > No problem. Just pull a snippet from a good Samaritan and let Pi test it on itself Now, I can use the reliable Qwen 3.6 Plus without busting my OpenCode Go sub, and the capable Kimi K2.6 without 404s The beauty of Pi is it can customize itself

raymel 👋

47,901 просмотров • 2 месяцев назад

THIS ENGINEER RUNS CLAUDE CODE WITHOUT PAYING ANTHROPIC A SINGLE DOLLAR RTX 5090 under the desk, Qwen 3.5 35B, 140 tokens per second Claude Code pointed at localhost instead of Anthropic’s servers override two environment variables and your API bill drops to zero he built a full-stack Next.js app from scratch to prove it works then showed every bug and limitation other YouTubers hide same setup I run with two GPUs and Qwen 3.6 27B full breakdown ↓

THIS ENGINEER RUNS CLAUDE CODE WITHOUT PAYING ANTHROPIC A SINGLE DOLLAR RTX 5090 under the desk, Qwen 3.5 35B, 140 tokens per second Claude Code pointed at localhost instead of Anthropic’s servers override two environment variables and your API bill drops to zero he built a full-stack Next.js app from scratch to prove it works then showed every bug and limitation other YouTubers hide same setup I run with two GPUs and Qwen 3.6 27B full breakdown ↓

leopardracer

29,756 просмотров • 2 месяцев назад

We just wrapped what began as an 8-hour challenge - and it ran for 200 hours without a failure Shoutout to the team for the hardcore engineering behind F.03 and the robust Helix models powering it

We just wrapped what began as an 8-hour challenge - and it ran for 200 hours without a failure Shoutout to the team for the hardcore engineering behind F.03 and the robust Helix models powering it

Brett Adcock

5,003,812 просмотров • 2 месяцев назад

🚨 One orchestrator. 10 parallel agents. 100+ tokens a second. All local. The Google Gemma team just dropped a MASSIVE demo for Gemma 4 26B. They built a concurrent workflow that lets the 26B model coordinate an entire team of sub-agents on your machine. Out of the box, the cookbook lets you run 10 parallel agents to: → Code an entire SVG art gallery in seconds → Translate text simultaneously → Generate ASCII art → Write parallel code Spinning up multi-agent systems locally has never looked this fast or this accessible. 100% free and open-source. repo link in 🧵↓

🚨 One orchestrator. 10 parallel agents. 100+ tokens a second. All local. The Google Gemma team just dropped a MASSIVE demo for Gemma 4 26B. They built a concurrent workflow that lets the 26B model coordinate an entire team of sub-agents on your machine. Out of the box, the cookbook lets you run 10 parallel agents to: → Code an entire SVG art gallery in seconds → Translate text simultaneously → Generate ASCII art → Write parallel code Spinning up multi-agent systems locally has never looked this fast or this accessible. 100% free and open-source. repo link in 🧵↓

Charly Wargnier

31,627 просмотров • 1 месяц назад

🔥 Introducing Firecrawl /search. Firecrawl just launched an insane feature to search and crawl in one shot. You heard that right! One API call to search the web and scrape any data you need for your AI agents. I took it for a spin in n8n:

🔥 Introducing Firecrawl /search. Firecrawl just launched an insane feature to search and crawl in one shot. You heard that right! One API call to search the web and scrape any data you need for your AI agents. I took it for a spin in n8n:

elvis

42,656 просмотров • 1 год назад

Parameter scaling just broke in front of me. I gave 90 math problems as images to 10 local vision models, 3 runs each, only consistent answers across all 3 runs counted. Two findings: > Gemma 4 was the most consistent family, 31B took the crown at 89.6%. > But Qwen 3.5 4B came 2 answers behind it. A 4B. Ranked 2nd out of 10. Vision-math isn't one skill, it's two: reading the image, then solving it. The real lesson for anyone running local: small ≠ weak. If you're building agentic workflows, finding the right model for each task matters more than reaching for the biggest one. In this test, the 4B ran far faster because of its size, scored higher, and left VRAM free for the rest of your stack. Full results: 🥇 Gemma 4 31B — 242/270 (89.6%) 🥈 Qwen 3.5 4B — 240/270 (88.9%) 🥉 Gemma 4 E4B — 222/270 (82.2%) 🥉 Qwen 3.6 27B — 222/270 (82.2%) 5. Gemma 4 26B A4B — 216/270 (80.0%) 6. Qwen 3.5 2B — 201/270 (74.4%) 7. Gemma 4 E2B — 192/270 (71.1%) 8. Qwen 3.6 35B A3B — 192/270 (71.1%) 9. Qwen 3.5 9B — 168/270 (62.2%) 10. Qwen 3.5 0.8B — 45/270 (16.7%) All GGUF + mmproj, Unsloth's Q6_K_XL quant.

Parameter scaling just broke in front of me. I gave 90 math problems as images to 10 local vision models, 3 runs each, only consistent answers across all 3 runs counted. Two findings: > Gemma 4 was the most consistent family, 31B took the crown at 89.6%. > But Qwen 3.5 4B came 2 answers behind it. A 4B. Ranked 2nd out of 10. Vision-math isn't one skill, it's two: reading the image, then solving it. The real lesson for anyone running local: small ≠ weak. If you're building agentic workflows, finding the right model for each task matters more than reaching for the biggest one. In this test, the 4B ran far faster because of its size, scored higher, and left VRAM free for the rest of your stack. Full results: 🥇 Gemma 4 31B — 242/270 (89.6%) 🥈 Qwen 3.5 4B — 240/270 (88.9%) 🥉 Gemma 4 E4B — 222/270 (82.2%) 🥉 Qwen 3.6 27B — 222/270 (82.2%) 5. Gemma 4 26B A4B — 216/270 (80.0%) 6. Qwen 3.5 2B — 201/270 (74.4%) 7. Gemma 4 E2B — 192/270 (71.1%) 8. Qwen 3.6 35B A3B — 192/270 (71.1%) 9. Qwen 3.5 9B — 168/270 (62.2%) 10. Qwen 3.5 0.8B — 45/270 (16.7%) All GGUF + mmproj, Unsloth's Q6_K_XL quant.

stevibe

22,882 просмотров • 2 месяцев назад

OpenClaw just went fully local. No cloud. No API bills. Zero cost AI agents running on your own computer. 🤯 This changes everything about automation in 2026. Pair OpenClaw with Ollama and you can run models like Qwen, Minimax, and Kimi directly on your machine. That means daily research agents, content pipelines, onboarding automations, and community updates running nonstop without paying per task. Most people still think powerful agents require subscriptions. They don’t anymore.

OpenClaw just went fully local. No cloud. No API bills. Zero cost AI agents running on your own computer. 🤯 This changes everything about automation in 2026. Pair OpenClaw with Ollama and you can run models like Qwen, Minimax, and Kimi directly on your machine. That means daily research agents, content pipelines, onboarding automations, and community updates running nonstop without paying per task. Most people still think powerful agents require subscriptions. They don’t anymore.

Julian Goldie SEO

18,996 просмотров • 4 месяцев назад

Metorial (@MetorialAI) makes it easy for AI agents to use tools and data. Deploy 600+ MCP integrations in three clicks and connect them to agents in a single function call. Open-source and the only serverless MCP platform built for multi-tenant systems.

Metorial (@MetorialAI) makes it easy for AI agents to use tools and data. Deploy 600+ MCP integrations in three clicks and connect them to agents in a single function call. Open-source and the only serverless MCP platform built for multi-tenant systems.

Y Combinator

15,341 просмотров • 9 месяцев назад

Ex-NVIDIA engineer who built Unsloth explained RL, kernels, reasoning, quantization, and agents in 2 hours 42 minutes - better than $5000 fine-tuning bootcamps. pick the base model -> write triton kernels for 2x faster fine-tune -> quantize to 4-bit -> run GRPO/DPO -> ship a reasoning model on your single GPU. That loop is why Unsloth is the default way to fine-tune Llama, Qwen, Gemma, and Phi on hardware you already own. Unsloth + Triton kernels + 4-bit quantization + GRPO/DPO + single-GPU fine-tuning - that's the stack. Watch and save it, then fine-tune your first model tonight.

Ex-NVIDIA engineer who built Unsloth explained RL, kernels, reasoning, quantization, and agents in 2 hours 42 minutes - better than $5000 fine-tuning bootcamps. pick the base model -> write triton kernels for 2x faster fine-tune -> quantize to 4-bit -> run GRPO/DPO -> ship a reasoning model on your single GPU. That loop is why Unsloth is the default way to fine-tune Llama, Qwen, Gemma, and Phi on hardware you already own. Unsloth + Triton kernels + 4-bit quantization + GRPO/DPO + single-GPU fine-tuning - that's the stack. Watch and save it, then fine-tune your first model tonight.

h100envy

492,892 просмотров • 1 месяц назад

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

147,197 просмотров • 1 месяц назад

Everyone is still asking if India can build its own AI. Sarvam stopped asking and shipped it. Raised $234M building India-first LLMs. 10 million API calls a day. Half a million hours of audio transcribed a month. In languages no global model bothered to learn. Built from India. Built for the world. Here's their story:

Everyone is still asking if India can build its own AI. Sarvam stopped asking and shipped it. Raised $234M building India-first LLMs. 10 million API calls a day. Half a million hours of audio transcribed a month. In languages no global model bothered to learn. Built from India. Built for the world. Here's their story:

rvivek

135,638 просмотров • 1 месяц назад

Gemma 4 can run on phones without an internet connection! 🤯 It can perform local agentic tasks, such as logging and analyzing trends. When connected, it can also make API calls. Want to try it yourself? Get the Google AI Edge App on iOS or Android. (🔊 Sound on for the demo!)

Gemma 4 can run on phones without an internet connection! 🤯 It can perform local agentic tasks, such as logging and analyzing trends. When connected, it can also make API calls. Want to try it yourself? Get the Google AI Edge App on iOS or Android. (🔊 Sound on for the demo!)

Google Gemma

759,181 просмотров • 4 месяцев назад

AI Agents can now connect to 100,000+ APIs instantly. Postman's AI Agent builder can turn any API into an MCP server in seconds without writing a single line of Code. You can use it in Claude, Cursor, Windsurf and other AI tools.

AI Agents can now connect to 100,000+ APIs instantly. Postman's AI Agent builder can turn any API into an MCP server in seconds without writing a single line of Code. You can use it in Claude, Cursor, Windsurf and other AI tools.

Shubham Saboo

79,818 просмотров • 1 год назад