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.

Unlimited-OCR is a 3B parameter model that parses entire 100-page PDFs in one shot — no page chunking, no lost context. +⁠32K context window, reads the whole document in a single pass +⁠93% on standard parsing benchmarks, +6 over baseline +⁠Under 0.11 error rate past page 40 — where... show more

0xMarioNawfal

261,238 subscribers

84,468 Aufrufe • vor 1 Monat •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

A peanut-sized Chinese model just dethroned Gemini at reading documents. GLM-OCR is a 0.9B parameter vision-language model. It scores 94.62 on OmniDocBench V1.5, ranking #1 overall. For context, it outperforms models 100x its size. 100% open-source. It works in two stages. 1. A layout engine detects every region in a document. 2. Each region gets read in parallel. The model predicts multiple tokens per step instead of one. That's what makes it so fast at small size. It handles things most OCR tools struggle with: > Complex tables and nested layouts > Handwritten text and stamps > Math formulas and code blocks > Mixed image-and-text documents You can run it locally through Ollama. It fits on edge devices with limited compute. Every expensive OCR API just got a free competitor.

A peanut-sized Chinese model just dethroned Gemini at reading documents. GLM-OCR is a 0.9B parameter vision-language model. It scores 94.62 on OmniDocBench V1.5, ranking #1 overall. For context, it outperforms models 100x its size. 100% open-source. It works in two stages. 1. A layout engine detects every region in a document. 2. Each region gets read in parallel. The model predicts multiple tokens per step instead of one. That's what makes it so fast at small size. It handles things most OCR tools struggle with: > Complex tables and nested layouts > Handwritten text and stamps > Math formulas and code blocks > Mixed image-and-text documents You can run it locally through Ollama. It fits on edge devices with limited compute. Every expensive OCR API just got a free competitor.

AlphaSignal

92,137 Aufrufe • vor 5 Monaten

A peanut-sized Chinese model just dethroned Gemini at reading documents. GLM-OCR is a 0.9B parameter vision-language model. It scores 94.62 on OmniDocBench V1.5, ranking #1 overall. For context, it outperforms models 100x its size. 100% open-source. It works in two stages. 1. A layout engine detects every region in a document. 2. Each region gets read in parallel. The model predicts multiple tokens per step instead of one. That's what makes it so fast at small size. It handles things most OCR tools struggle with: > Complex tables and nested layouts > Handwritten text and stamps > Math formulas and code blocks > Mixed image-and-text documents You can run it locally through Ollama. It fits on edge devices with limited compute. Every expensive OCR API just got a free competitor.

A peanut-sized Chinese model just dethroned Gemini at reading documents. GLM-OCR is a 0.9B parameter vision-language model. It scores 94.62 on OmniDocBench V1.5, ranking #1 overall. For context, it outperforms models 100x its size. 100% open-source. It works in two stages. 1. A layout engine detects every region in a document. 2. Each region gets read in parallel. The model predicts multiple tokens per step instead of one. That's what makes it so fast at small size. It handles things most OCR tools struggle with: > Complex tables and nested layouts > Handwritten text and stamps > Math formulas and code blocks > Mixed image-and-text documents You can run it locally through Ollama. It fits on edge devices with limited compute. Every expensive OCR API just got a free competitor.

Jafar Najafov

13,630 Aufrufe • vor 5 Monaten

NVIDIA just made paying for AI feel optional. Open model, a million tokens of context, free tier with no per-token cost, runs on your own hardware. Entire codebases, whole data rooms, a year of chat logs, all swallowed in one prompt. No chunking, no RAG, no rate limit theater. The closed-AI premium has 90 days to defend itself. Bookmark this and come back. Open beat closed. Again.

NVIDIA just made paying for AI feel optional. Open model, a million tokens of context, free tier with no per-token cost, runs on your own hardware. Entire codebases, whole data rooms, a year of chat logs, all swallowed in one prompt. No chunking, no RAG, no rate limit theater. The closed-AI premium has 90 days to defend itself. Bookmark this and come back. Open beat closed. Again.

shmidt

295,692 Aufrufe • vor 3 Monaten

NVIDIA just made AI detect objects 10x faster by deleting one step. It's called LocateAnything, and it removes the biggest bottleneck no one else was fixing in vision-language models. Normally a model builds each bounding box one coordinate token at a time. 100 objects means thousands of tokens before an answer. NVIDIA scrapped that: their Parallel Box Decoding predicts the whole box in a single forward pass, as one atomic unit. → 12.7 boxes/sec on one H100 → 10x faster than Qwen3-VL → +3.8% F1 on LVIS, accuracy up, not down → 3B params, runs on one consumer GPU Treating the box as one unit keeps its coordinates tied together, which is why accuracy climbed instead of falling. One model handles detection, GUI grounding, OCR, and document understanding, ready for computer-use agents, robotics, and document pipelines. 100% open source, weights, code, demo, and paper all live.

NVIDIA just made AI detect objects 10x faster by deleting one step. It's called LocateAnything, and it removes the biggest bottleneck no one else was fixing in vision-language models. Normally a model builds each bounding box one coordinate token at a time. 100 objects means thousands of tokens before an answer. NVIDIA scrapped that: their Parallel Box Decoding predicts the whole box in a single forward pass, as one atomic unit. → 12.7 boxes/sec on one H100 → 10x faster than Qwen3-VL → +3.8% F1 on LVIS, accuracy up, not down → 3B params, runs on one consumer GPU Treating the box as one unit keeps its coordinates tied together, which is why accuracy climbed instead of falling. One model handles detection, GUI grounding, OCR, and document understanding, ready for computer-use agents, robotics, and document pipelines. 100% open source, weights, code, demo, and paper all live.

Alvaro Cintas

202,075 Aufrufe • vor 2 Monaten

Your coding agent can run commands, use tools, and touch your entire codebase And most of you have ZERO controls on it Harden AIF fixes that Local security model reviews every tool call in context and stops the unnecessary or risky ones before they execute Runs fully local Repo context stays private Dashboard + activity logs + searchable sessions so you can see exactly what your agent did Free forever for individual devs curl -fsSL | sh This is the way

Your coding agent can run commands, use tools, and touch your entire codebase And most of you have ZERO controls on it Harden AIF fixes that Local security model reviews every tool call in context and stops the unnecessary or risky ones before they execute Runs fully local Repo context stays private Dashboard + activity logs + searchable sessions so you can see exactly what your agent did Free forever for individual devs curl -fsSL | sh This is the way

Hasan Toor

13,244 Aufrufe • vor 13 Tagen

Google Translate is cooked after this. A developer built a local AI translation engine that runs 40 languages entirely on your own laptop. It's called LibreTranslate. No API key. No usage limits. No sending your documents to Google's servers. You install it once. It runs forever. Here's what it handles: → Paste text. Translated instantly. → Drop in a file. Outputs the translated version. → Point it at a URL. Returns the page in your language. → Build it into your own app via its local REST API. The speed is not the story. The privacy is. Google Translate reads every sentence you paste into it. Legal contracts. Medical records. Internal emails. Client documents. Every word goes to their servers and stays there. LibreTranslate runs entirely offline. Nothing leaves your machine. Ever. The numbers: → 40 languages supported → Runs on CPU -- no GPU needed → Self-hosted in under 5 minutes → REST API built in for developers → 10K+ stars on GitHub 100% open source. MIT licensed. Price: $0. Google charges nothing for Translate either but it charges you something else. GitHub:

Google Translate is cooked after this. A developer built a local AI translation engine that runs 40 languages entirely on your own laptop. It's called LibreTranslate. No API key. No usage limits. No sending your documents to Google's servers. You install it once. It runs forever. Here's what it handles: → Paste text. Translated instantly. → Drop in a file. Outputs the translated version. → Point it at a URL. Returns the page in your language. → Build it into your own app via its local REST API. The speed is not the story. The privacy is. Google Translate reads every sentence you paste into it. Legal contracts. Medical records. Internal emails. Client documents. Every word goes to their servers and stays there. LibreTranslate runs entirely offline. Nothing leaves your machine. Ever. The numbers: → 40 languages supported → Runs on CPU -- no GPU needed → Self-hosted in under 5 minutes → REST API built in for developers → 10K+ stars on GitHub 100% open source. MIT licensed. Price: $0. Google charges nothing for Translate either but it charges you something else. GitHub:

Rimsha Bhardwaj

89,676 Aufrufe • vor 2 Monaten

1 mini PC that fits in a palm, with no monthly token bill attached to it. Most people run their AI through a browser tab. Every prompt, every document, every half-finished idea leaves the machine and lands on someone else's server. This ORICO mini PC runs the model locally. The assistant lives inside the box, not in a data center 2,000 miles away. Small enough to slide into a bag. Powerful enough that you stop noticing it is not a desktop. You pay once for hardware instead of every month for limits. No outage that takes your assistant down with it. No terms of service deciding what your files are worth. Plug it in anywhere, and the assistant is already there, offline, waiting. The smallest machine on the desk is the only one that keeps its mouth shut.

1 mini PC that fits in a palm, with no monthly token bill attached to it. Most people run their AI through a browser tab. Every prompt, every document, every half-finished idea leaves the machine and lands on someone else's server. This ORICO mini PC runs the model locally. The assistant lives inside the box, not in a data center 2,000 miles away. Small enough to slide into a bag. Powerful enough that you stop noticing it is not a desktop. You pay once for hardware instead of every month for limits. No outage that takes your assistant down with it. No terms of service deciding what your files are worth. Plug it in anywhere, and the assistant is already there, offline, waiting. The smallest machine on the desk is the only one that keeps its mouth shut.

AiMind

82,625 Aufrufe • vor 19 Tagen

JENSEN HUANG UNVEILED A BOARD THAT RUNS 1 TRILLION PARAMETER AI MODELS. THE $249 NVIDIA BOX UNDER YOUR DESK KILLS A $200/MONTH AI BILL FOR $5 IN ELECTRICITY jensen held it up on stage with one hand and called it the architecture that runs the future of ai. that same technology now ships in a $249 box smaller than your wallet the jetson orin nano super pulls 7-25 watts and does 67 trillion ai operations per second. llama 3, mistral and deepseek run locally with no api fees and no data leaving your machine most developers pay $2,400 a year across chatgpt, openai api, claude pro and cursor. the jetson costs $314 in year one and $60 a year after. 2 year savings hit $4,431 install ollama with one command, change one line of code to point at localhost, and every tool built for openai works identically. zero rewrites, zero rate limits cloud subscriptions keep getting more expensive and rate limits keep getting tighter. the people who own the box in 2026 are going to look very far ahead in 2028 bookmark this and read the article below

JENSEN HUANG UNVEILED A BOARD THAT RUNS 1 TRILLION PARAMETER AI MODELS. THE $249 NVIDIA BOX UNDER YOUR DESK KILLS A $200/MONTH AI BILL FOR $5 IN ELECTRICITY jensen held it up on stage with one hand and called it the architecture that runs the future of ai. that same technology now ships in a $249 box smaller than your wallet the jetson orin nano super pulls 7-25 watts and does 67 trillion ai operations per second. llama 3, mistral and deepseek run locally with no api fees and no data leaving your machine most developers pay $2,400 a year across chatgpt, openai api, claude pro and cursor. the jetson costs $314 in year one and $60 a year after. 2 year savings hit $4,431 install ollama with one command, change one line of code to point at localhost, and every tool built for openai works identically. zero rewrites, zero rate limits cloud subscriptions keep getting more expensive and rate limits keep getting tighter. the people who own the box in 2026 are going to look very far ahead in 2028 bookmark this and read the article below

starmex

54,492 Aufrufe • vor 3 Monaten

1.7 billion free tokens per month. A month ago i showed you how to route claude code through free providers. someone just shipped the cleanest version of this setup yet… it's called Freellmapi 13,400+ stars on github, MIT licensed, takes 2 minutes to install. what it does: stacks the free tiers of 16 different LLM providers behind one local API. point claude code, codex, or cursor at that one endpoint, and it automatically routes your calls across all 16 free pools. The 16 providers it covers: Google, Groq, Cerebras, Mistral, OpenRouter, GitHub Models, Cloudflare, Cohere, NVIDIA, HuggingFace, Ollama Cloud, Kilo, Pollinations, LLM7, OVH, and OpenCode Zen. if you sign up to all 16 and add your free API keys, you get roughly 1.7 billion free tokens per month combined. ▫️ How to install (one command) curl -fsSL bash this runs the whole thing locally on your machine through Docker. once it's up, open paste your provider keys on the Keys page, and grab the unified API key from the dashboard. that's the key you point your apps at. With this, claude code stops hitting your monthly cap because every prompt routes through the 16 free pools instead of your paid plan. and if one provider rate-limits mid-conversation, freellmapi falls over to the next one automatically so your session never breaks. repo: Free, MIT-licensed, runs on your laptop or a $5 VPS.

1.7 billion free tokens per month. A month ago i showed you how to route claude code through free providers. someone just shipped the cleanest version of this setup yet… it's called Freellmapi 13,400+ stars on github, MIT licensed, takes 2 minutes to install. what it does: stacks the free tiers of 16 different LLM providers behind one local API. point claude code, codex, or cursor at that one endpoint, and it automatically routes your calls across all 16 free pools. The 16 providers it covers: Google, Groq, Cerebras, Mistral, OpenRouter, GitHub Models, Cloudflare, Cohere, NVIDIA, HuggingFace, Ollama Cloud, Kilo, Pollinations, LLM7, OVH, and OpenCode Zen. if you sign up to all 16 and add your free API keys, you get roughly 1.7 billion free tokens per month combined. ▫️ How to install (one command) curl -fsSL bash this runs the whole thing locally on your machine through Docker. once it's up, open paste your provider keys on the Keys page, and grab the unified API key from the dashboard. that's the key you point your apps at. With this, claude code stops hitting your monthly cap because every prompt routes through the 16 free pools instead of your paid plan. and if one provider rate-limits mid-conversation, freellmapi falls over to the next one automatically so your session never breaks. repo: Free, MIT-licensed, runs on your laptop or a $5 VPS.

Axel Bitblaze 🪓

48,825 Aufrufe • vor 2 Monaten

THIS FREE CHINESE AI MODEL RUNS LOCALLY FOREVER AND BUILDS ANYTHING YOU CAN IMAGINE - INCLUDING FULL OPEN WORLD GAMES GLM 5.2 - open, local, free forever - no bills, no limits, no subscription want an open world game with multiplayer - describe it, it builds - want business automation - builds that too - literally anything running 24/7 same as Claude and GPT at $200/month - on your own machine, forever free - saves $2,400/year in subscriptions responds in 2-3 seconds - your computer, your speed, nobody in the queue ahead of you whoever finds out about this today saves thousands and ships a real product before everyone still waiting for the perfect tool

THIS FREE CHINESE AI MODEL RUNS LOCALLY FOREVER AND BUILDS ANYTHING YOU CAN IMAGINE - INCLUDING FULL OPEN WORLD GAMES GLM 5.2 - open, local, free forever - no bills, no limits, no subscription want an open world game with multiplayer - describe it, it builds - want business automation - builds that too - literally anything running 24/7 same as Claude and GPT at $200/month - on your own machine, forever free - saves $2,400/year in subscriptions responds in 2-3 seconds - your computer, your speed, nobody in the queue ahead of you whoever finds out about this today saves thousands and ships a real product before everyone still waiting for the perfect tool

Noisy

23,541 Aufrufe • vor 2 Monaten

New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.

New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.

elvis

11,303 Aufrufe • vor 25 Tagen

Moonshot AI is casually giving developers free daily access to Kimi K3 😳 no subscription no upfront payment just sign in and start using one of the largest open AI models available what you get for $0: - Kimi K3 with 2.8T parameters - 1M token context window - strong coding and reasoning performance - native vision capabilities - free daily credits that refresh automatically why this is worth checking: > access a frontier model without paying API fees > long context for large codebases and documents > works on web, desktop, mobile, and CLI getting started takes less than 2 minutes: 1. go to 2. create a free account 3. Kimi K3 is available as the default model 4. start chatting or coding with your daily free credits bonus: Moonshot Together lets you invite friends for a chance to earn 3, 7, 15, 30, or even 365 days of Kimi Membership through its rewards program benchmark highlights: > 2.8T parameter MoE model > 1M context window > strong performance across coding, browsing, and reasoning benchmarks important: free credits reset daily, rate limits apply on the free tier, and the open-weight release is expected on July 27 A simple way to try one of the latest frontier AI models without paying for API access

Moonshot AI is casually giving developers free daily access to Kimi K3 😳 no subscription no upfront payment just sign in and start using one of the largest open AI models available what you get for $0: - Kimi K3 with 2.8T parameters - 1M token context window - strong coding and reasoning performance - native vision capabilities - free daily credits that refresh automatically why this is worth checking: > access a frontier model without paying API fees > long context for large codebases and documents > works on web, desktop, mobile, and CLI getting started takes less than 2 minutes: 1. go to 2. create a free account 3. Kimi K3 is available as the default model 4. start chatting or coding with your daily free credits bonus: Moonshot Together lets you invite friends for a chance to earn 3, 7, 15, 30, or even 365 days of Kimi Membership through its rewards program benchmark highlights: > 2.8T parameter MoE model > 1M context window > strong performance across coding, browsing, and reasoning benchmarks important: free credits reset daily, rate limits apply on the free tier, and the open-weight release is expected on July 27 A simple way to try one of the latest frontier AI models without paying for API access

K2S

23,110 Aufrufe • vor 1 Monat

Testing the new Gemma 4 12B (QAT) vision and OCR capabilities locally with LM Studio. # The setup: - GPU: NVIDIA RTX 4060 (8GB VRAM) - CPU: Intel i7 - Runner: LM Studio - Config: 32k context, 38 layers offloaded, Flash Attention enabled - Speed: ~14 tokens/sec decode throughput # The test: I gave it a screenshot of Google AI Studio. Prompt: "clone this. give me a single html file" # The result: A solid one shot replication. It successfully mapped out the layout, recognized the UI text, and structured the divs correctly, with only minor differences from the original. Results available at the end of the video. Quite capable for a 12B model running on budget consumer hardware. A gpu that costs only $300. # Why the architecture under the hood is notable: Unlike traditional models that rely on heavy, separate vision and audio encoders, Gemma 4 12B uses a unified, encoder free architecture. It bypasses separate multi stage encoders. Uses a 35M parameter vision embedder to project raw 48x48 pixel patches directly to the LLM hidden dimension. Local multimodal development is becoming highly accessible on standard hardware. If you've spun up Gemma 4 12B locally, what setup are you using and what kind of throughput are you seeing?

Testing the new Gemma 4 12B (QAT) vision and OCR capabilities locally with LM Studio. # The setup: - GPU: NVIDIA RTX 4060 (8GB VRAM) - CPU: Intel i7 - Runner: LM Studio - Config: 32k context, 38 layers offloaded, Flash Attention enabled - Speed: ~14 tokens/sec decode throughput # The test: I gave it a screenshot of Google AI Studio. Prompt: "clone this. give me a single html file" # The result: A solid one shot replication. It successfully mapped out the layout, recognized the UI text, and structured the divs correctly, with only minor differences from the original. Results available at the end of the video. Quite capable for a 12B model running on budget consumer hardware. A gpu that costs only $300. # Why the architecture under the hood is notable: Unlike traditional models that rely on heavy, separate vision and audio encoders, Gemma 4 12B uses a unified, encoder free architecture. It bypasses separate multi stage encoders. Uses a 35M parameter vision embedder to project raw 48x48 pixel patches directly to the LLM hidden dimension. Local multimodal development is becoming highly accessible on standard hardware. If you've spun up Gemma 4 12B locally, what setup are you using and what kind of throughput are you seeing?

Alok

25,717 Aufrufe • vor 3 Monaten

here's how the whole thing works. claude code doesn't care what's behind the API. it just sends requests and expects responses. so i pointed it at my own machine instead of anthropic's servers. llama-server runs the model locally. LiteLLM sits in between and translates the API format. claude code thinks it's talking to claude. it's talking to qwen on localhost. the setup: 2x 3090s, 38 layers on GPU, 10 on CPU. 128K context window. generation is only 7 tok/s but the tradeoff is worth it. 128K means the agent can hold an entire project in memory without losing context midtask. claude code alone loads a 17.5K token system prompt on every request. tool definitions, safety rules, agent behavior. that's your baseline before you even say hello. pushed as far as i could tonight. what surprised me most wasn't the speed. it was the iteration quality. first prompt gave me a working particle sim. second prompt, the model read its own 564 lines, understood the architecture, and added trails, explosions, gravity wells, bloom effects. no handholding. 4bit quantized. 45GB on two consumer cards. running a full coding agent autonomously. detailed article coming. full benchmarks, hardware breakdowns, engine debugging, code quality. everything from setup to what broke and why.

here's how the whole thing works. claude code doesn't care what's behind the API. it just sends requests and expects responses. so i pointed it at my own machine instead of anthropic's servers. llama-server runs the model locally. LiteLLM sits in between and translates the API format. claude code thinks it's talking to claude. it's talking to qwen on localhost. the setup: 2x 3090s, 38 layers on GPU, 10 on CPU. 128K context window. generation is only 7 tok/s but the tradeoff is worth it. 128K means the agent can hold an entire project in memory without losing context midtask. claude code alone loads a 17.5K token system prompt on every request. tool definitions, safety rules, agent behavior. that's your baseline before you even say hello. pushed as far as i could tonight. what surprised me most wasn't the speed. it was the iteration quality. first prompt gave me a working particle sim. second prompt, the model read its own 564 lines, understood the architecture, and added trails, explosions, gravity wells, bloom effects. no handholding. 4bit quantized. 45GB on two consumer cards. running a full coding agent autonomously. detailed article coming. full benchmarks, hardware breakdowns, engine debugging, code quality. everything from setup to what broke and why.

Sudo su

37,623 Aufrufe • vor 6 Monaten

LOOP RAT: THE TECH UNDER AN AUTONOMOUS CODING LOOP no framework, no service, no database a dozen files of bash and python, plus one per loop one shift runs six phases: > preflight - won't start if state/HALT exists, spend is gone, or the loop's already running > act - runs under a hard timeout. shell gathers facts, the model only judges > verify - runs the plan's verify: command. "tests pass" isn't proof. the exit code is > guard - fingerprints the tree. blocks a denylisted path, an oversized diff, anything shaped like a secret > grade - a second agent, fresh context, grades against rubrics it never wrote > receipt - writes receipt.json, appends the trace, updates the checkpoint three brakes stack in order: > daily spend cap, checked before the shift starts > per-call cap, checked before each model call > hard timeout for whatever's already running scheduling runs on schedule.yml and one cron line run-due is idempotent - a missed window is a skipped shift, never a backlog dumped at once The official ca: 0x642d30c84211ade7768fe557fbaed7224e2068c7 50 tests cover the parsers, the lock, the guard, the ledger under concurrent writers, and the kill switch

LOOP RAT: THE TECH UNDER AN AUTONOMOUS CODING LOOP no framework, no service, no database a dozen files of bash and python, plus one per loop one shift runs six phases: > preflight - won't start if state/HALT exists, spend is gone, or the loop's already running > act - runs under a hard timeout. shell gathers facts, the model only judges > verify - runs the plan's verify: command. "tests pass" isn't proof. the exit code is > guard - fingerprints the tree. blocks a denylisted path, an oversized diff, anything shaped like a secret > grade - a second agent, fresh context, grades against rubrics it never wrote > receipt - writes receipt.json, appends the trace, updates the checkpoint three brakes stack in order: > daily spend cap, checked before the shift starts > per-call cap, checked before each model call > hard timeout for whatever's already running scheduling runs on schedule.yml and one cron line run-due is idempotent - a missed window is a skipped shift, never a backlog dumped at once The official ca: 0x642d30c84211ade7768fe557fbaed7224e2068c7 50 tests cover the parsers, the lock, the guard, the ledger under concurrent writers, and the kill switch

Mr. Buzzoni

11,827 Aufrufe • vor 10 Tagen

Cancelled ChatGPT -> Built JARVIS -> Pays $0 -> it works offline + it's smarter than the $20/month version. No WiFi needed, no cloud, no API keys, no rate limits, no queues, no $20/month just to ask a server in Virginia for the weather. Just a local model running directly on the laptop hardware, voice activated, system integrated, controlling apps, answering questions, doing the work. Iron Man had JARVIS embedded in his suit, this guy has it embedded in his MacBook and it works on a plane, in a basement, on a remote cabin with zero signal. OpenAI is burning $700,000 a day on infrastructure to deliver something this guy runs for free. Anthropic charges $200/month for unlimited Claude access, microsoft built Copilot into every product they sell. This guy skipped all of it, downloaded a model and made his laptop the smartest device in the room. No subscription. No login. No internet. No data sent anywhere ever. The most powerful AI assistant on earth is now the one running locally on hardware you already own. ChatGPT charges you to think slower, he pays nothing and thinks alone, he made it himself.

Cancelled ChatGPT -> Built JARVIS -> Pays $0 -> it works offline + it's smarter than the $20/month version. No WiFi needed, no cloud, no API keys, no rate limits, no queues, no $20/month just to ask a server in Virginia for the weather. Just a local model running directly on the laptop hardware, voice activated, system integrated, controlling apps, answering questions, doing the work. Iron Man had JARVIS embedded in his suit, this guy has it embedded in his MacBook and it works on a plane, in a basement, on a remote cabin with zero signal. OpenAI is burning $700,000 a day on infrastructure to deliver something this guy runs for free. Anthropic charges $200/month for unlimited Claude access, microsoft built Copilot into every product they sell. This guy skipped all of it, downloaded a model and made his laptop the smartest device in the room. No subscription. No login. No internet. No data sent anywhere ever. The most powerful AI assistant on earth is now the one running locally on hardware you already own. ChatGPT charges you to think slower, he pays nothing and thinks alone, he made it himself.

Defileo🔮

154,607 Aufrufe • vor 4 Monaten

i just ran Google's brand new Unsloth Gemma4 12B dense GGUF on my RTX 4060 using llama.cpp + CUDA 13.2 21 tokens per second. on a budget consumer GPU. locally. no API. no cloud. no subscription. and the benchmarks are absolutely cooked # first let's talk architecture because this is genuinely different every multimodal model you've used has a frozen vision encoder + frozen audio encoder + LLM backbone glued together Gemma 4 12B is different it's a single decoder only transformer. that's it. vision? raw 48×48 pixel patches → one matmul → projected directly into the LLM audio? raw 16kHz signal sliced into 40ms frames → linear projection → same LLM input space no encoder tax. no latency penalty. no fragmented memory to put the encoder savings in perspective: old Gemma 4 26B approach: - 550M param vision encoder (frozen) - 300M param audio encoder (frozen) - LLM backbone Gemma 4 12B: - 35M param vision embedder (a single matmul) - no audio encoder at all - LLM backbone handles EVERYTHING 550M → 35M for vision alone. that's a 15x reduction this is why the gemma-4-12b-it-Q4_K_M.gguf is just 6.6 GBs!!! and it has 256K native context context # Benchmarks: AIME 2026 (math olympiad): 77.5% GPQA Diamond (expert science): 78.8% LiveCodeBench v6 (real code): 72% Codeforces ELO: 1659 MMLU Pro: 77.2% MATH-Vision: 79.7% BigBench Extra Hard: 53% inference → llama.cpp, LM Studio, vLLM, SGLang llamacpp flags: -m "gemma-4-12b-it-Q4_K_M.gguf" -ngl 99 -c 8000 -v --port 8080 Available on huggingface now! Link below

Alok

281,007 Aufrufe • vor 3 Monaten

This Chinese developer launched Llama 70B locally on a MacBook on a plane and for a full 11 hours without internet ran client projects. He was sitting by the window on a transatlantic flight with a MacBook Pro M4 with 64 GB of memory. WiFi on board cost $25 for the flight. He declined. No cloud API, no connection to Anthropic or OpenAI servers, no internet at all. Just a local Llama 3.3 70B on bf16 and his own orchestrator script. The model runs through llama.cpp. Generation speed, 71 tokens per second. Context around 60,000 tokens. Memory usage, 48.6 GiB out of 64. Battery at takeoff, 3 hours 21 minutes. And he gave the orchestrator this system prompt before takeoff: "You are an offline orchestrator running on a single MacBook. There is no network. The only resources you have are local files in /Users/dev/work, the Llama 70B inference server at localhost:8080, and a battery budget of 3 hours 21 minutes. Process the queue at /Users/dev/work/queue.jsonl (one client task per line). For each task: draft → run local evals → save artefact to /Users/dev/work/done/. Save context checkpoints every 12 tasks so you can resume after a battery swap. Stop only on empty queue or when battery drops below 5%." So the system knows exactly what resources it is running on. It knows it has no connection to the outside world for the next 11 hours. It knows it has finite memory and a finite battery. It knows the human will not intervene until the plane lands. The system runs in 1 loop. Takes a task from the queue, runs it through inference, saves the artifact, writes a checkpoint. Task after task, just like that. And only when the battery drops below 5% does the orchestrator automatically pause, waits for the laptop to switch to the backup power bank, and continues from the last checkpoint. Here is what the system actually writes in his log during the flight: "saved context checkpoint 8 of 12 (pos_min = 488, pos_max = 50118, size = 62.813 MiB)" "restored context checkpoint (pos_min = 488, pos_max = 50118)" "prompt processing progress: n_tokens = 50 / 60 818" "task 37016 done | tps = 71 s tokens text → /Users/dev/work/done/proposal_westside.md" Outside the window, clouds, blue sky, and no WiFi. On the tray, 1 MacBook, an open terminal on 2 screens, and an inference server on localhost. From what I have observed, this is the cleanest offline AI workflow I have seen in the past year: 11 hours of flight, $0 for WiFi, and the entire client queue closed before landing.

This Chinese developer launched Llama 70B locally on a MacBook on a plane and for a full 11 hours without internet ran client projects. He was sitting by the window on a transatlantic flight with a MacBook Pro M4 with 64 GB of memory. WiFi on board cost $25 for the flight. He declined. No cloud API, no connection to Anthropic or OpenAI servers, no internet at all. Just a local Llama 3.3 70B on bf16 and his own orchestrator script. The model runs through llama.cpp. Generation speed, 71 tokens per second. Context around 60,000 tokens. Memory usage, 48.6 GiB out of 64. Battery at takeoff, 3 hours 21 minutes. And he gave the orchestrator this system prompt before takeoff: "You are an offline orchestrator running on a single MacBook. There is no network. The only resources you have are local files in /Users/dev/work, the Llama 70B inference server at localhost:8080, and a battery budget of 3 hours 21 minutes. Process the queue at /Users/dev/work/queue.jsonl (one client task per line). For each task: draft → run local evals → save artefact to /Users/dev/work/done/. Save context checkpoints every 12 tasks so you can resume after a battery swap. Stop only on empty queue or when battery drops below 5%." So the system knows exactly what resources it is running on. It knows it has no connection to the outside world for the next 11 hours. It knows it has finite memory and a finite battery. It knows the human will not intervene until the plane lands. The system runs in 1 loop. Takes a task from the queue, runs it through inference, saves the artifact, writes a checkpoint. Task after task, just like that. And only when the battery drops below 5% does the orchestrator automatically pause, waits for the laptop to switch to the backup power bank, and continues from the last checkpoint. Here is what the system actually writes in his log during the flight: "saved context checkpoint 8 of 12 (pos_min = 488, pos_max = 50118, size = 62.813 MiB)" "restored context checkpoint (pos_min = 488, pos_max = 50118)" "prompt processing progress: n_tokens = 50 / 60 818" "task 37016 done | tps = 71 s tokens text → /Users/dev/work/done/proposal_westside.md" Outside the window, clouds, blue sky, and no WiFi. On the tray, 1 MacBook, an open terminal on 2 screens, and an inference server on localhost. From what I have observed, this is the cleanest offline AI workflow I have seen in the past year: 11 hours of flight, $0 for WiFi, and the entire client queue closed before landing.

Blaze

1,842,664 Aufrufe • vor 4 Monaten

the 24gb vram tier is enough for most builder work in 2026. gemma 4 31b dense on my rog scar 18 just autonomously built a production hero section in one prompt, one html file and 5 minutes end to end. hardware: rog scar 18, rtx 5090 laptop 24gb vram. model: google gemma 4 31b dense at q4_k_m quant, using 22.8 of 24gb. engine: llama.cpp built for blackwell (sm_120). harness: hermes agent with native tool parsing. speed: 15 tok/s sustained, 94 watts, 50c. flags i used: ./build/bin/llama-server -m ~/models/gemma4-31b/google_gemma-4-31B-it-Q4_K_M.gguf -ngl 99 -c 131072 -np 1 -fa on --cache-type-k q4_0 --cache-type-v q4_0 --jinja --host 127.0.0.1 --port 8080 if you own 24gb vram in 2026, you have enough for most ui work, most agentic coding, most autonomous builds. no subscription, no one logging your prompts. a dense open model on consumer hardware shipping real software on your desk. this was the warmup. full page next on same hardware, then the octopus invaders final multifile autonomous challenge.

the 24gb vram tier is enough for most builder work in 2026. gemma 4 31b dense on my rog scar 18 just autonomously built a production hero section in one prompt, one html file and 5 minutes end to end. hardware: rog scar 18, rtx 5090 laptop 24gb vram. model: google gemma 4 31b dense at q4_k_m quant, using 22.8 of 24gb. engine: llama.cpp built for blackwell (sm_120). harness: hermes agent with native tool parsing. speed: 15 tok/s sustained, 94 watts, 50c. flags i used: ./build/bin/llama-server -m ~/models/gemma4-31b/google_gemma-4-31B-it-Q4_K_M.gguf -ngl 99 -c 131072 -np 1 -fa on --cache-type-k q4_0 --cache-type-v q4_0 --jinja --host 127.0.0.1 --port 8080 if you own 24gb vram in 2026, you have enough for most ui work, most agentic coding, most autonomous builds. no subscription, no one logging your prompts. a dense open model on consumer hardware shipping real software on your desk. this was the warmup. full page next on same hardware, then the octopus invaders final multifile autonomous challenge.

Sudo su

19,576 Aufrufe • vor 4 Monaten

you're paying $20/mo for something your $500 GPU can already do. Gemma 4 26B A4B QAT MoE + Hermes Agent running on a single RTX 4060 (8GB VRAM). Built a vision capable, 100% free, 100% local, private AI assistant that lives in my Chrome browser. No API keys. No cloud. No subscriptions. 100% vibe coded. 0% handholding. It has full context of whatever's on my screen can answer questions, summarize pages, extract data, and see images. Same local model handles everything, no external calls, ever. keep reading for the model and hermes agent tips i learnt while building this locally. Here's the exact setup for anyone running local LLMs on 6-8 GB VRAM: llama.cpp server flags (on my NVIDIA RTX 4060 8gb VRAM): -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf --cache-type-k q8_0 --cache-type-v q8_0 -c 150000 --port 8080 Throughput with quantization: Prefill: 200-250 tokens/sec Decode: 20-25 tokens/sec reduce context if oom on 6 gb vram card. Key learnings: - Quantize KV cache to q8 for faster prefill/decode. Prefill goes from 100-150 (unquantized) to 200-250 tok/s (q8). - But watch out, once actual context grows past ~50k tokens on high entropy workloads, q8 KV quantization can cause hallucinations. Low entropy workloads are mostly unaffected. If you see it happening, drop the quantization. This is common across all local models. - In Hermes Agent settings -> Memory & Context, bump compression threshold from default 0.5 to 0.7. Default triggers way too frequent context compression and eats time. Up next: add persistent memory, web search, tool calling, streaming output and whatever you suggest. Running a 26B MoE with vision + 150k context window on 8GB VRAM would've sounded impossible 6 months ago. Works the same on the NVIDIA RTX 3060 Ti, 3070, 4060 Ti, 5060, 2080, or any 8GB card. VRAM is the only requirement. Local AI agents are closer than people think. You just need to know where the knobs are. Model's Unsloth quant hugging face link in the comments. Have you tried Hermes agent by Nous Research yet? What are you building with local LLMs? Drop it below, let's see what this community is shipping.

you're paying $20/mo for something your $500 GPU can already do. Gemma 4 26B A4B QAT MoE + Hermes Agent running on a single RTX 4060 (8GB VRAM). Built a vision capable, 100% free, 100% local, private AI assistant that lives in my Chrome browser. No API keys. No cloud. No subscriptions. 100% vibe coded. 0% handholding. It has full context of whatever's on my screen can answer questions, summarize pages, extract data, and see images. Same local model handles everything, no external calls, ever. keep reading for the model and hermes agent tips i learnt while building this locally. Here's the exact setup for anyone running local LLMs on 6-8 GB VRAM: llama.cpp server flags (on my NVIDIA RTX 4060 8gb VRAM): -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf --cache-type-k q8_0 --cache-type-v q8_0 -c 150000 --port 8080 Throughput with quantization: Prefill: 200-250 tokens/sec Decode: 20-25 tokens/sec reduce context if oom on 6 gb vram card. Key learnings: - Quantize KV cache to q8 for faster prefill/decode. Prefill goes from 100-150 (unquantized) to 200-250 tok/s (q8). - But watch out, once actual context grows past ~50k tokens on high entropy workloads, q8 KV quantization can cause hallucinations. Low entropy workloads are mostly unaffected. If you see it happening, drop the quantization. This is common across all local models. - In Hermes Agent settings -> Memory & Context, bump compression threshold from default 0.5 to 0.7. Default triggers way too frequent context compression and eats time. Up next: add persistent memory, web search, tool calling, streaming output and whatever you suggest. Running a 26B MoE with vision + 150k context window on 8GB VRAM would've sounded impossible 6 months ago. Works the same on the NVIDIA RTX 3060 Ti, 3070, 4060 Ti, 5060, 2080, or any 8GB card. VRAM is the only requirement. Local AI agents are closer than people think. You just need to know where the knobs are. Model's Unsloth quant hugging face link in the comments. Have you tried Hermes agent by Nous Research yet? What are you building with local LLMs? Drop it below, let's see what this community is shipping.

Alok

36,691 Aufrufe • vor 2 Monaten