+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Optimization & Performance (https://www.datasculpting.ai/inference/forumdisplay.php?fid=10)
+--- Forum: Quantization (https://www.datasculpting.ai/inference/forumdisplay.php?fid=40)
+--- Thread: quant choices for 70B local for Mistral (/showthread.php?tid=726)
quant choices for 70B local for Mistral - vrambandit - 10-03-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
Just sharing a setup that ended up working reasonably well: Kimi, MLX, Threadripper box, with a lot of attention on MoE serving.
Feel free to tear it apart if you see something dumb.
For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.