Recent content by Easy Rhino

Oops! The 4b one. 4B parameter model (128k context window) With Q4 https://ollama.com/library/gemma3:4b

it is very good. i have it running with the updated Ollama version and new Rocm/mesa libs and it flies using the 6750 XT! Over 60 tps.

The inscription on the One Ring is in Black Speech, a language created by Sauron for the servants of Mordor, and it is written in Tengwar, an Elvish script. The Black Speech is described as a harsh and rough language, designed to be the sole language of all Sauron's followers, though it was not...

This is a "do you use linux?" thread, not a "Windows is terrible and everyone but the trolls know it" thread. Stay on topic.

It does seem "fairly fun." I think when i refer to the Civ style aspect of the game, I am referring to moving units around on the big map turn based style.

After playing for a few hours I do like the CIV style gameplay since it adds another element to the strategy. The skirmishes remind me of COH and COH2 which is great. It is $30 right now but yet I am still not sure if it is worth it since they released DLC for an additional 30...

I wanted to play/purchase COH3 when it was first released a couple of years ago. However reviews mostly all said it was trash. I have played COH and COH2 for hundreds and hundreds of hours. Fast forward to this weekend and I see they have some big 2.0 patch out and reviews seem improved but...

But can it run Crysis?

I'll never go with an Nvidia card until they finally go open source and put their drivers in the linux kernel!

What's amazing is that their M1 chip is still incredibly powerful. It runs OSX and all LLMs and other tasks better and with more power efficiency than anything else out there. I hope we get more Linux spins that work on Apple Silicon because there is a lot to gain from the work of Apple's...

Given that games don't look all that better and are certainly not any more immersive than they were 10 years ago, $250. Let's be honest, an APU should be enough these days to run visually impressive titles at 1440p 60fps. That would be actual technological progress. Instead we are stuck with...

Yea, it is discouraging that the free models are all pretty bad. I mean, none of them are all that great at boiler plate. Copilot recognizes what I am trying to do and it adjusts on the fly. Pretty great for getting the boring stuff out of the way.

I have tried deepseek-coder-v2 for chat and codellama, starcoder2, and qwen2.5-coder 1.5B for code completion and all of them are horrible compared to straight up copilot.

Yes and no. My current 6750 XT is not "supported" by Ollama but runs using ROCm with an additional flag. Ollama is actively working on direct support of more AMD cards. Direct software support means faster TPS for a lot of their models.

I will be upgrading to the 9700 XT 16 GB once the Ollama developers support it.