+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Optimization & Performance (https://www.datasculpting.ai/inference/forumdisplay.php?fid=10)
+--- Forum: Context / KV Cache (https://www.datasculpting.ai/inference/forumdisplay.php?fid=41)
+--- Thread: draft model choices: setup advice (/showthread.php?tid=483)
draft model choices: setup advice - cacheline - 09-25-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
Maybe useful as a starting point: MLX on B200, keeping tokens/sec in mind from the start.
If someone wants the exact settings I can clean them up and post them.
For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.
Re: draft model choices: setup advice - cacheline - 09-25-2026
Quote:Thought I'd post a small recipe because a lot of threads ask similar things.
A couple things I'd check first. On mini PC, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it. Turns out 'just one more test' was a lie.
Re: draft model choices: setup advice - pixelspark - 09-27-2026
Quote:Quote:Thought I'd post a small recipe because a lot of threads ask similar things.
subscribed, curious where this lands.
Re: draft model choices: setup advice - routecrate - 09-28-2026
Did a small comparison this afternoon. The issue went away once I changed one setting and restarted the stack cleanly.
Re: draft model choices: setup advice - cacheline - 09-28-2026
same here on my side.
Re: draft model choices: setup advice - mlxgarden - 09-28-2026
What exact setup are you running? Is this local-only or are you routing anything externally?
Re: draft model choices: setup advice - relayforge - 09-29-2026
Quote:What exact setup are you running? Is this local-only or are you routing anything externally?
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at router policy.
Re: draft model choices: setup advice - dockkite69 - 09-29-2026
What worked for me was pretty simple. On 4090, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.