+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Optimization & Performance (https://www.datasculpting.ai/inference/forumdisplay.php?fid=10)
+--- Forum: Performance Tuning (https://www.datasculpting.ai/inference/forumdisplay.php?fid=42)
+--- Thread: consumer GPU serving economics with MLX (/showthread.php?tid=849)
consumer GPU serving economics with MLX - marbletrack - 10-07-2026
Did a bit of testing and thought I'd post the result here.
I tried this with DeepSeek using SGLang on Threadripper box. The headline result was better than I expected, but KV cache pressure still ended up being the limiting factor.
Nothing scientific here, just practical notes from a real setup.
I care more about stability than squeezing the last possible tokens/sec out of it.
If I had to summarize the lesson so far, it would be that clean setup and observability beat clever guesses.