Recent content by csendesmark

I also bought it on the 3 years anniversary, it is good game.

It should be fit into the 20GB VRAM, Will check a different Gemma 27B model tomorrow. ----------- latter ---- Somewhat better performance with this Q4_K_M 16.5 GB https://huggingface.co/lmstudio-community/gemma-3-27b-it-GGUF

Gave a shot: Q4_K_M 16.5 GB https://huggingface.co/DevQuasar/google.gemma-3-27b-it-qat-q4_0-unquantized-GGUF

Which Q? Please tell me the exact model.

Thank You W1zzard!!! Much appreciated! :love: I agree 100%!

Using QWEN3 30B Q6_K 41/48 getting 14.2 tks while watching youtube. When Vivaldi closed: When I asked for the definition of a "point"

Hope they will produce a 32GB VRAM version too! :toast:

We need more cases supporting vertical GPU mounting with at least 4 slot thickness, while the rest of the slots are available on the mainboard! Please Be Quiet, Cooler Master, Fractal Design!

New, supposedly super efficient QWEN 3 is here https://huggingface.co/Qwen/Qwen3-8B — 63 token/s with Q8 https://huggingface.co/Qwen/Qwen3-30B-A3B — 18 tokens/s with Q6_K https://huggingface.co/Qwen/Qwen3-235B-A22B — n/a :D

What monster rig you have? And also, what speeds you can get? I could get one more of the kit I have to run it, but it would be still like 0.7 token/s or maybe even less :D

So this is the 32GB version of the AMD Radeon RX 9070 XT. Too bad it will cost double or more!

So cute :D

I am not sure about the actual devs, they do what the management demanding from them. So they need to rush and crunch - I am pretty sure they could finish and polish all TES games nicely, Consider the wide scope they always aiming for. More time (and money) needed for that. So I will not damn...

The Skyblivion mod is labor of love by fans who are not expecting to get paid. The mod Team would finish it even if only they going to play it.