I like it so much, and it’s my go-to search tool. Sometimes it struggles to identify official websites, but that only happens in about 1 out of every 100 searches.

I wish it had image search though.

It was Microsoft outlook copilot + x series x

For your hardware, the VRam is not enough to run 27b but, I’d recommend Qwen 3.5 9b for image / text to text.

And I’m planning to experiment with Qwen 3.8 9b for text to text.

4_k_m quantization is the sweet spot for performance and ram usage.

Also, I find Llama cpp is better than Ollama in terms of performance.

Local 27b models are good enough for most tasks.

Can’t wait to buy one of these from Ebay for 10% of the price next year.

Accurate and guaranteed!

They should allow quick unpolished genuine videos. I watch them all the time.

I use LibreWolf, where it’s enabled by default. Unfortunately, it broke a few sites for me. I recall two specific cases one a furniture store site with a 3D product viewer that stopped working, and an airline website that showed graphic glitches when I tried to print my ticket

Nebula exists but I subscribed to it like during COVID with Curiosity Stream bundle, however, I find their UI confusing and content discovery was very hard.