Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Advice for AI engineers 💡 A small Visual Language Model fine-tuned on your custom dataset is as accurate as GPT-5... ... and costs 50 times less For example, LFM2.5-VL-1.6B by Liquid AI running locally at full speed with llama.cpp ↓

paulabartabajo_'s profile picture

Pau Labarta Bajo

70,127 subscribers

11,388 Aufrufe • vor 23 Tagen •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Advice for AI engineers 💡 Small Audio LMs + Tool-calling LMs running locally are as fast as cloud speech APIs... ... but cost $0 per request and keep your data private. For example, LFM2.5-Audio-1.5B + LFM2-1.2B-Tool by Liquid AI ↓
0:37

Advice for AI engineers 💡 Small Audio LMs + Tool-calling LMs running locally are as fast as cloud speech APIs... ... but cost $0 per request and keep your data private. For example, LFM2.5-Audio-1.5B + LFM2-1.2B-Tool by Liquid AI ↓

Pau Labarta Bajo

38,442 Aufrufe • vor 5 Monaten

Advice for AI engineers 💡 A local AI assistant is just a while loop, an LLM and a set of tools. Here's a step-by-step lesson on how to build one from scratch with Liquid AI LFM2-24B-A2B running on llama.cpp. No cloud APIs. Enjoy ↓
57:09

Advice for AI engineers 💡 A local AI assistant is just a while loop, an LLM and a set of tools. Here's a step-by-step lesson on how to build one from scratch with Liquid AI LFM2-24B-A2B running on llama.cpp. No cloud APIs. Enjoy ↓

Pau Labarta Bajo

15,463 Aufrufe • vor 1 Monat

train YOLOv9 on your dataset tutorial - run inference with a pre-trained COCO model - fine-tune model on custom dataset - evaluate the trained model - run inference with a fine-tuned model blogpost: ↓ read more
0:30

train YOLOv9 on your dataset tutorial - run inference with a pre-trained COCO model - fine-tune model on custom dataset - evaluate the trained model - run inference with a fine-tuned model blogpost: ↓ read more

SkalskiP

111,792 Aufrufe • vor 2 Jahren

Sheepy-T: A fully open-source instruction-tuned language model based on GPT-J running locally on iPhone 14. Reply for beta access via TestFlight.
0:25

Sheepy-T: A fully open-source instruction-tuned language model based on GPT-J running locally on iPhone 14. Reply for beta access via TestFlight.

Kevin Kwok

102,354 Aufrufe • vor 3 Jahren

This video is at normal speed. Gemma 4 12B MLX version running locally at 50 tokens/sec. Thank you Google DeepMind team. This model feels really solid for a lot of small local tasks and everyday AI workflows.
0:50

This video is at normal speed. Gemma 4 12B MLX version running locally at 50 tokens/sec. Thank you Google DeepMind team. This model feels really solid for a lot of small local tasks and everyday AI workflows.

AshutoshShrivastava

19,782 Aufrufe • vor 27 Tagen

🔥 We fine-tuned Gemma 3 using Unsloth AI on a custom instruction dataset scraped and built with . The model is now able to answer questions about OpenAI Agents SDK documentation. Check out the demo below👇
0:48

🔥 We fine-tuned Gemma 3 using Unsloth AI on a custom instruction dataset scraped and built with . The model is now able to answer questions about OpenAI Agents SDK documentation. Check out the demo below👇

Eric Ciarla (hiring)

28,794 Aufrufe • vor 1 Jahr

LFM2-VL support with GGUF and llama.cpp 🥳 You can now run these tiny, hyper-efficient VLMs on your watch! We released quantized checkpoints for LFM2-VL-450M and LFM2-VL-1.6B on Hugging Face
0:59

LFM2-VL support with GGUF and llama.cpp 🥳 You can now run these tiny, hyper-efficient VLMs on your watch! We released quantized checkpoints for LFM2-VL-450M and LFM2-VL-1.6B on Hugging Face

Maxime Labonne

19,947 Aufrufe • vor 10 Monaten

QVAC SDK will support in 0.9.0 (gonna be release in ~10 days) LoRA fine-tuning directly on-device, letting developers customize LLMs with their own data without sending anything to the cloud. You just load a base model, point it at your training dataset, and get a lightweight LoRA adapter back — all running locally. The fine-tuned model can then be used for inference immediately, with no extra setup. Why it matters: LoRA (Low-Rank Adaptation) fine-tuning lets you specialize a general-purpose language model for your specific use case — like matching a brand's tone, mastering domain terminology, or following a particular output format — using a fraction of the compute a full fine-tune would require. QVAC handles the entire workflow locally: dataset preparation, training with configurable hyperparameters, checkpoint saving, and seamless inference with the resulting adapter. Your data never leaves the device. The developer experience: Fine-tuning with QVAC is as simple as calling "sdk.finetune()" with your dataset and a few hyperparameters. Training runs entirely on your local hardware, produces a compact LoRA adapter file, and supports pause/resume so you can stop a job and pick it back up without losing progress. The result plugs straight into QVAC's inference pipeline — no model conversion, no deployment step, just immediate local completions with your fine-tuned model.
0:33

QVAC SDK will support in 0.9.0 (gonna be release in ~10 days) LoRA fine-tuning directly on-device, letting developers customize LLMs with their own data without sending anything to the cloud. You just load a base model, point it at your training dataset, and get a lightweight LoRA adapter back — all running locally. The fine-tuned model can then be used for inference immediately, with no extra setup. Why it matters: LoRA (Low-Rank Adaptation) fine-tuning lets you specialize a general-purpose language model for your specific use case — like matching a brand's tone, mastering domain terminology, or following a particular output format — using a fraction of the compute a full fine-tune would require. QVAC handles the entire workflow locally: dataset preparation, training with configurable hyperparameters, checkpoint saving, and seamless inference with the resulting adapter. Your data never leaves the device. The developer experience: Fine-tuning with QVAC is as simple as calling "sdk.finetune()" with your dataset and a few hyperparameters. Training runs entirely on your local hardware, produces a compact LoRA adapter file, and supports pause/resume so you can stop a job and pick it back up without losing progress. The result plugs straight into QVAC's inference pipeline — no model conversion, no deployment step, just immediate local completions with your fine-tuned model.

Paolo Ardoino 🤖

42,271 Aufrufe • vor 2 Monaten

OpenAI: "Look at our new AI-powered internet search! with a fine-tuned model!" Perplexity: "Look at our AI-powered internet search combining multiple models!" Google: "We built a custom pipeline for AI summaries!" Microsoft: "We did AI search built around Bing years ago!" Claude:
1:09

OpenAI: "Look at our new AI-powered internet search! with a fine-tuned model!" Perplexity: "Look at our AI-powered internet search combining multiple models!" Google: "We built a custom pipeline for AI summaries!" Microsoft: "We did AI search built around Bing years ago!" Claude:

Ethan Mollick

260,082 Aufrufe • vor 1 Jahr

GPT-5 is live across the Vercel AI Cloud, and it's available: • on AI Gateway • as a model in • in our new open-source vibe coding platform
1:24

GPT-5 is live across the Vercel AI Cloud, and it's available: • on AI Gateway • as a model in • in our new open-source vibe coding platform

Vercel

14,965 Aufrufe • vor 10 Monaten

You can now have an AI researcher running on your laptop 24/7 for free! Running Qwen3-35B-A3B with llama.cpp and a 4-bit quant from Unsloth
0:30

You can now have an AI researcher running on your laptop 24/7 for free! Running Qwen3-35B-A3B with llama.cpp and a 4-bit quant from Unsloth

Lewis Tunstall

118,360 Aufrufe • vor 1 Monat

This Changes Everything. Google Edge Gallery is a MUST for every smartphone, this is a straight up lifesaver. Imagine you’re on a trip, no internet, completely different language, trying to eat something but the packaging makes zero sense… and your phone just handles it instantly. And that’s just a SMALL example of on-device AI running locally without internet… this is insane.
0:27

This Changes Everything. Google Edge Gallery is a MUST for every smartphone, this is a straight up lifesaver. Imagine you’re on a trip, no internet, completely different language, trying to eat something but the packaging makes zero sense… and your phone just handles it instantly. And that’s just a SMALL example of on-device AI running locally without internet… this is insane.

TechDroider

18,319 Aufrufe • vor 2 Monaten

I put together a minimalistic pure-Rust, CPU-only implementation of the recent LFM2.5-8B-A1B language model from Liquid AI that you can directly link into your Rust projects😎
12:19

I put together a minimalistic pure-Rust, CPU-only implementation of the recent LFM2.5-8B-A1B language model from Liquid AI that you can directly link into your Rust projects😎

Maxime Chevalier

13,922 Aufrufe • vor 25 Tagen

A voice agent powered by gpt-oss. Running locally on my macBook. Demo recorded in a Waymo with WiFi turned off. I'm still on my space game voice AI kick, obviously. Code link below. For conversational voice AI, you want to set the gpt-oss reasoning behavior to "low". (The default is "medium".) Notes on how to do that and a jinja template you can use are in the repo. The LLM in the demo video is the big, 120B version of gpt-oss. You can use the smaller, 20B model for this, of course. But OpenAI really did a cool thing here designing the 120B model to run in "just" 80GB of VRAM. And the llama.cpp mlx inference is fast: ~250ms TTFT. Running a big model on-device feels like a time warp into the future of AI.
4:35

A voice agent powered by gpt-oss. Running locally on my macBook. Demo recorded in a Waymo with WiFi turned off. I'm still on my space game voice AI kick, obviously. Code link below. For conversational voice AI, you want to set the gpt-oss reasoning behavior to "low". (The default is "medium".) Notes on how to do that and a jinja template you can use are in the repo. The LLM in the demo video is the big, 120B version of gpt-oss. You can use the smaller, 20B model for this, of course. But OpenAI really did a cool thing here designing the 120B model to run in "just" 80GB of VRAM. And the llama.cpp mlx inference is fast: ~250ms TTFT. Running a big model on-device feels like a time warp into the future of AI.

kwindla

202,113 Aufrufe • vor 11 Monaten

Don’t DIY your AI: building a custom Agentforce agent is as simple as describing the job and integrating it directly into your workflow—no separate models, hyperscalers, databases, or AI engineers needed! With all apps, data, AI, and workflows seamlessly integrated on the Salesforce Platform, humans + agents = customer success. This is what AI was meant to be! #DF24
2:36

Don’t DIY your AI: building a custom Agentforce agent is as simple as describing the job and integrating it directly into your workflow—no separate models, hyperscalers, databases, or AI engineers needed! With all apps, data, AI, and workflows seamlessly integrated on the Salesforce Platform, humans + agents = customer success. This is what AI was meant to be! #DF24

Marc Benioff

44,725 Aufrufe • vor 1 Jahr

Sam Altman recently said: “GPT-OSS has strong real-world performance comparable to o4-mini—and you can run it locally on your phone.” Many believed running a 20B-parameter model on mobile devices was still years away. At Nexa AI, we’ve built our foundation on deep on-device AI technology—turning that vision into reality. Today, GPT-OSS is running fully local on mobile devices through our app, Nexa Studio. Real performance on Snapdragon Gen 5: - 17 tokens/sec decoding speed - < 3 seconds Time-to-First-Token Developers can now use NexaSDK to build their own local AI apps powered by GPT-OSS. What this unlocks: - Real reasoning models running locally - The next wave of AI Agent use cases—without cloud limits - True data privacy: your data never leaves your device Appreciation to OpenAI Sam Altman Greg Brockman and the entire leadership team for pushing the boundaries of the open-source AI community. Thanks to Qualcomm for the partnership, and to Manoj Khilnani and Chun-Po (Jerry) Chang for the incredible collaboration.
0:31

Sam Altman recently said: “GPT-OSS has strong real-world performance comparable to o4-mini—and you can run it locally on your phone.” Many believed running a 20B-parameter model on mobile devices was still years away. At Nexa AI, we’ve built our foundation on deep on-device AI technology—turning that vision into reality. Today, GPT-OSS is running fully local on mobile devices through our app, Nexa Studio. Real performance on Snapdragon Gen 5: - 17 tokens/sec decoding speed - < 3 seconds Time-to-First-Token Developers can now use NexaSDK to build their own local AI apps powered by GPT-OSS. What this unlocks: - Real reasoning models running locally - The next wave of AI Agent use cases—without cloud limits - True data privacy: your data never leaves your device Appreciation to OpenAI Sam Altman Greg Brockman and the entire leadership team for pushing the boundaries of the open-source AI community. Thanks to Qualcomm for the partnership, and to Manoj Khilnani and Chun-Po (Jerry) Chang for the incredible collaboration.

NEXA AI

197,453 Aufrufe • vor 8 Monaten

This means AI Gateway requests can now be enriched with custom metadata to break down LLM costs by model, provider, user, and tag. Observe, track, and unify spend, whether for internal company usage, or for AI platform billing at scale. Try our API by asking your agent:
1:00

This means AI Gateway requests can now be enriched with custom metadata to break down LLM costs by model, provider, user, and tag. Observe, track, and unify spend, whether for internal company usage, or for AI platform billing at scale. Try our API by asking your agent:

Vercel

23,743 Aufrufe • vor 3 Monaten

Incredible to see the Aria Digital Twin (ADT) dataset leveraged here! 🚀 ADT is a game-changer for AI—it bridges the gap between real-world sensor data and 1:1 3D virtual reconstructions by providing a hyper-accurate "gold-standard" benchmark. Using this data, the RADIO-ViPE team proved that "uncalibrated" predictions can be nearly as accurate as those from expensive, high-end sensor rigs. This is a massive step forward for robots and AI systems understanding 3D spaces in real-time. 👓✨ Paper: Dataset: 💡Nathan Yan
0:30

Incredible to see the Aria Digital Twin (ADT) dataset leveraged here! 🚀 ADT is a game-changer for AI—it bridges the gap between real-world sensor data and 1:1 3D virtual reconstructions by providing a hyper-accurate "gold-standard" benchmark. Using this data, the RADIO-ViPE team proved that "uncalibrated" predictions can be nearly as accurate as those from expensive, high-end sensor rigs. This is a massive step forward for robots and AI systems understanding 3D spaces in real-time. 👓✨ Paper: Dataset: 💡Nathan Yan

Project Aria @Meta

26,780 Aufrufe • vor 1 Monat

Deepseek running locally and privately for autocompletion in VSCode! 🙌 In less than a minute, I'll show you how to download Deepseek-coder and set it as the autocompletion model in VSCode. You’ll need to use ollama to download the model and CodeGPT to select it as the autocompletion model. Enjoy the best models running locally with :)
0:49

Deepseek running locally and privately for autocompletion in VSCode! 🙌 In less than a minute, I'll show you how to download Deepseek-coder and set it as the autocompletion model in VSCode. You’ll need to use ollama to download the model and CodeGPT to select it as the autocompletion model. Enjoy the best models running locally with :)

Daniel San

991,070 Aufrufe • vor 1 Jahr

Qwen 3.6 35B running at over 100 tokens per second on my $5,399 MacBook Pro M5 Max. This is the best local AI model I have ever run. 128GB of unified memory. No cloud. No API costs. No rate limits. Just raw local inference at speeds I didn't think were possible on a laptop. This model is more intelligent than GPT 5 on benchmarks. Running locally. On a MacBook. For free after the hardware cost. I said local AI would never compete with frontier. I'm starting to rethink that. The gap is closing faster than anyone expected.
1:04

Qwen 3.6 35B running at over 100 tokens per second on my $5,399 MacBook Pro M5 Max. This is the best local AI model I have ever run. 128GB of unified memory. No cloud. No API costs. No rate limits. Just raw local inference at speeds I didn't think were possible on a laptop. This model is more intelligent than GPT 5 on benchmarks. Running locally. On a MacBook. For free after the hardware cost. I said local AI would never compete with frontier. I'm starting to rethink that. The gap is closing faster than anyone expected.

BridgeMind

62,800 Aufrufe • vor 1 Monat