+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Inference Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=9)
+--- Forum: TensorRT-LLM (https://www.datasculpting.ai/inference/forumdisplay.php?fid=37)
+--- Thread: serving on Blackwell (/showthread.php?tid=1423)
serving on Blackwell - kernelmike - 10-17-2026
Has anyone else run into this?
My current setup is Ollama with M3 Max, and I keep running into small local stacks.
Not looking for the perfect answer, mostly what worked in real use.
For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.
Re: serving on Blackwell - localpatch - 10-18-2026
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Mistral and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.
Re: serving on Blackwell - visionforge - 10-18-2026
Interesting, I hadn't tried that. I ended up in about the same place using TensorRT-LLM. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: serving on Blackwell - kernelgrid - 10-18-2026
subscribed, curious where this lands.
Re: serving on Blackwell - kernelmike - 10-18-2026
I'd approach it in a boring order. On M3 Max, 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: serving on Blackwell - routecrate - 10-18-2026
My first guess would be this: On 4090, the easiest win is often to back off the aggressive settings and see whether the problem survives.
Re: serving on Blackwell - audioforge - 10-18-2026
Quote:My first guess would be this: On 4090, the easiest win is often to back off the aggressive settings and see whether the problem survives.
That matches what I was seeing. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
If you post your exact settings, people here can probably narrow it down pretty fast.
Re: serving on Blackwell - rasterbench - 10-18-2026
What exact setup are you running? Is this local-only or are you routing anything externally?