ViewTube

A local LLM can now write real code on hardware from 2020 but the biggest question isn't how smart the model is. It's whether ...

Qwen 3.8 27b is an open weight AI model that you can run on your PC, if you have a high-end video card with 32GB of VRAM.

We have a new version from the Ornith team with 1.5. The version 1.0 was a pretty great model, can this one continue to impress?

In this demo, we showcase how the ASUS Ascent GX10, powered by the @NVIDIA GB10 Grace Blackwell Superchip, runs large ...

Qwen 3.8 Is Here! This 27B AI Runs LOCALLY Qwen 3.8 is here — and the local AI game just got VERY interesting. In this ...

In this video, I look at the long awaited Qwen3.8-27B model. Both what it can do and how to serve it at the maximum tokens per ...

It seems like we're in the middle of mini-revolution around local LLMs, and I was trying to benchmark the newest Qwen 3.8 27B for ...

Qwen 3.8 27B is small enough to run on my DGX Spark — so I gave it the same brutal multi-hour tasks I gave DeepSeek, and put ...

And after this, check out our related video exploring how to choose the right local LLM for your hardware and workload. #ollama ...

Join the Community: https://discord.gg/MRESQnf4R4 Companion Deep-dive article on Substack: ...

This is Jarvis. He talks, he remembers everything we've ever worked on, he pushes back when my ideas don't add up, and he ...

Mario, the creator of Pi, shares the story behind his lightweight AI coding agent. Built out of a desire for control, minimalism, and ...

In this episode of Ben's Open Tabs, I finally take the plunge in learning how to run AI models directly on my own own machine with ...

In this tutorial, we build a practical local LLM workflow from the ground up—from installation and model setup to serving requests ...

Ollama #localllm #Ollamainlocal Want to run an LLM locally on your computer without depending on a cloud AI API?

Run Qwen3.5 locally with Ollama 2. Connect a local LLM with VS Code 3. Use AI to chat, edit, explain and generate code 4.

In this video: Why applications use external LLM APIs The basics of local LLM inference Running Gemma 3 4B with Ollama ...

In this Tim Unscripted how‑to, I walk through wiring up the Pi terminal‑native coding agent to a locally served model on a ...

Run AI Models Locally on Your Own System with Ollama + Antigravity!** In this video, I'll show you **step-by-step how to ...

Qwen3.8 27B parameter model is out and it's exactly the kind of model you can (and should) be running locally. In this video I put ...