I benched every gaming gpu tier from 8 to 24gb and wrote one guide for all of you

So you know exactly what your card can run, then i checked it against steam's 15 most owned gpus and 14 of them run a 27b today 8gb, the 5060, 4060, 3050, 3060 ti, 3070 and the 4060 and 5060

Sudo suOct 518

I still can't get over how close the qwen 3.8 125b landed to the glm 5.3 flash 320b building the same floating tree.

So watch! here is every number from both runs in one place, serve settings included, save it if you're picking a local model for agent builds glm 5.3 flash

Sudo suOct 57

I had two of the best local models build the same floating tree

Glm 5.3 flash at 320b and qwen 3.8 flash next at 125b, and despite the size gap look where both landed glm 5.3 flash: 320b moe with 18b active, nvidia's nvfp4 weights split over 2x dgx spark, served with vllm

Sudo suOct 540

Qwen 3.8 27B + TensorFold built a game for my Hardball 3D challenge in 3h 14m.

Of the three builds, it’s the most playable, even more so than the GPT-6 Luna baseline. Decode · 90th percentile: 42.37 tok/s Prefill · mean: 160.55 tok/s Run details:

Alfredo Artiles 🇨🇺Oct 52