+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Drivers / Frameworks / Toolkits (https://www.datasculpting.ai/inference/forumdisplay.php?fid=8)
+--- Forum: Apple / MLX (https://www.datasculpting.ai/inference/forumdisplay.php?fid=33)
+--- Thread: M3 Max for local use for DeepSeek (/showthread.php?tid=176)
Pages:
1
2
Re: M3 Max for local use for DeepSeek - mlxgarden - 09-12-2026
Maybe, but I had the opposite result. I've seen people blame long context when the real issue was much more mundane.
Re: M3 Max for local use for DeepSeek - mellowstream - 09-12-2026
Quote:Maybe, but I had the opposite result. I've seen people blame long context when the real issue was much more mundane.
My first guess would be this: On A6000, the easiest win is often to back off the aggressive settings and see whether the problem survives. Once you know the plain path works, then add the faster path back in piece by piece.
Re: M3 Max for local use for DeepSeek - circuitwire58 - 09-14-2026
Thanks, that helps. That matches what I saw on 7900 XTX. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing. The logs were somehow calmer than I was.
Re: M3 Max for local use for DeepSeek - torchshed - 09-14-2026
What worked for me was pretty simple. On GB200, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.
Re: M3 Max for local use for DeepSeek - labnest - 09-14-2026
I tested this tonight. My result was mixed: first run looked bad, second run looked normal. The main thing that moved was latency, not quality.