I've spent my whole week converting my stack over from Qwen 27B over to Niko's Strata setup with Qwen…
I've spent my whole week converting my stack over from Qwen 27B over to Niko's Strata setup with Qwen Flash Next, optimizing, tweaking, benching and its been unbelievable what my 2x3090s can do now. I've always seen people on here posting insane Voxel one shots and honestly I've…
I made this with the HC-Q8 Qwen 3.8 Flash Next quant I put on hugging face in ROCmFPX.
This was a one shot prompt and took 24 hours. No looping. No issues in OMP. So How did I do the graphical parts? I had Qwen 3.8 Flash Next reach out and AGY (Google) Command Line to actually
Bro borrowed his mom’s iPhone and turned it into a second GPU for his MacBook.
Backburner runs Qwen 3.8 27B across a 24GB M4 Pro MacBook and an iPhone 17 Pro Max, connected by a 10Gb/s USB-C cable. How does a 27B model fit? It uses IQ4_XS quantization, roughly 4 bits per
Qwen 3.8 Max with the same prompt as Fable 5.5 earlier on my timeline.
This is the second best one in my opinion. GLM-5.3 is the last one and should be ready soon.
You have reached the end of the archive
All of qwen38