@paulabartabajo_: Advice for AI engineers The best way to learn local AI is to build with local AI. 7 hands-on webinars from the last 7 m…
Summary
A collection of 7 hands-on, open-source webinars from the past 7 months focused on building with local AI and small language models, all running on-device.
View Cached Full Text
Cached at: 06/13/26, 01:06 AM
Advice for AI engineers 💡
The best way to learn local AI is to build with local AI.
7 hands-on webinars from the last 7 months. All open-source. All small LFM models. All running on-device.
The full collection 🧵 (1/7)↓
Advice for AI engineers
The best way to learn local AI is to build with local AI.
7 hands-on webinars from the last 7 months. All open-source. All small LFM models. All running on-device.
The full collection (1/7)↓
-
Fine-tuning LFM2-VL for image classification.
-
Building a 100% local Audio-to-Speech CLI with LFM2-Audio.
-
Fine-tuning LFM2-350M for browser control with GRPO and OpenEnv.
-
Local video captioning with LFM2.5-VL-1.6B and WebGPU.
-
Build your own local AI coding assistant.
-
Build a wildfire detection system with a Vision Language Model and satellite images.
-
Building on-device voice agents.
Hope this helps.
Every week I write and send a newsletter with hands-on advice, directly from the trenches of an AI lab.
You can subscribe for free so you get my email every Saturday.
https://paulabartabajo.substack.com
Thanks for the share @paulabartabajo_ will be implementing soon all of these..
Similar Articles
@TheAhmadOsman: Local AI is the future Learning how to run Opensource models (Inference), how to evaluate them systematically (Evals), …
A tweet from @TheAhmadOsman emphasizes that local AI is the future and recommends learning skills like running open-source models, conducting evals, and customizing models through fine-tuning.
@TheAhmadOsman: DROP EVERYTHING Everything you need to get started with Local AI completely FOR FREE Hardware. Software. Anything in be…
A comprehensive free guide and resource for setting up local AI, covering hardware foundations, software stacks, and model mechanics, promoted via a Twitter thread.
@paulabartabajo_: Advice for AI engineers A small Visual Language Model fine-tuned on your custom dataset is as accurate as GPT-5... ... …
A tweet claims that a small visual language model fine-tuned on custom data can match GPT-5 accuracy while costing 50× less, citing Liquid AI’s 1.6B model running locally with llama.cpp.
Have you ever seriously tried local AI?
The author argues that local AI is underestimated due to usability barriers, and introduces their project Euler to make local AI as seamless as cloud AI with privacy and ownership advantages.
@awnihannun: The video from @angeloskath on local agentic AI with MLX is excellent. I also hear it's one of the most viewed videos i…
A tweet highlights an excellent WWDC video by Angelos Kath on building local agentic AI with MLX, noting rapid progress in open-weight models and hardware capabilities.