Happiness in #4 boxes. When local ai becomes more than just a small "hobby"

Four DGX Sparks (Asus Ascent GX10) to run DeepSeek v4 flash, Qwen 3.8 27B and hopefully next week GLM 5.3. Only challenge: frequent LLM switches due to new releases...

Michael KerkhoffAug 21

I've been trying to find a good solution local AI.

I tried using Qwen 3.8 27B on my M5 Max w/ 128GB and it has not been a good experience. I have a desktop computer running Ubuntu with a 5090 and quite honestly that experience has been much better, but it is a remote connection

Rich · Atom Tan StudioAug 213

Wanted To See Max Speeds of 6 Instances of Qwen 3.8 27B w/ 2 x 3090 NVLINK and DFLASH 2

Qwen3.8-27B • 6 parallel coding agents • Total: 8,352 tokens in 10s • Aggregate: 330.6 tok/s peak · 812.0 tok/s sustained • Per-stream: 147.8 high / 145.7 low / 147.1 avg tok/s • TTFT

Tech2WildAug 2113

Qwen 3.8 saves you $20/month on Claude.

All it takes is a $5,000 Mac Studio/DGX Spark upgrade. Now, how long until we break even?

LousAug 21