FRAMEWIREIndonesiaUpdated Aug 15Live wire
0:00 / 0:00

After deploying Qwen 3.8-27B locally, I learned another knowledge

Dgx spark is not suitable for running Dense models Different model architectures have different throughput requirements for underlying computing power and memory bandwidth. If a dense model does not do quantification and KV management well, no matter how powerful the hardware is, it will not work. Sure enough, practice brings true knowledge, let’s feel the speed.

LonelyAug 158
0:00 / 0:00

QWEN 3.8:27b made this as a one shot prompt for me in 20m!

All while running locally on my machine. Kinda crazy

PawelAug 15
0:00 / 0:00

Agentic Task: Install K3s in your own slicervm

Left: DeepSeek V4 Flash 0731 - 2x DGX Sparks Right: Qwen 3.8 27B (FP8) - 1x RTX 6000 Pro 40 (ish) tok/s gen vs 88 tok/s Why do they both feel "slow"? Thinking aka "variant" - they're spending a lot of tokens on reasoning.

Alex EllisAug 158
0:00 / 0:00

Same prompt: Qwen 3.8 FP8 on the left, Qwen 3.6 FP8 on the right.

The difference in design taste isn't even close. Though it's hard to tell if 3.8 was specifically fine-tuned for this task—the level of polish is almost unreal.

机器学习我不学Aug 15