09-21-2026, 07:30 AM
Ran a quick check on my box. I couldn't reproduce the slowdown until I pushed context much higher.
|
local video generation really usable yet for Mistral
|
|
09-21-2026, 07:30 AM
Ran a quick check on my box. I couldn't reproduce the slowdown until I pushed context much higher.
09-21-2026, 07:56 AM
A couple things I'd check first. On M3 Max, 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.
09-21-2026, 08:32 AM
I tested this tonight. The issue went away once I changed one setting and restarted the stack cleanly. The surprise was that memory pressure showed up before throughput collapsed.
small models can still be good
09-24-2026, 08:40 AM
Ran a quick check on my box. On A6000 with MLX, I saw basically the same behavior. The main thing that moved was latency, not quality.
image models by night, local pipelines by day
09-24-2026, 08:56 AM
Quote:Ran a quick check on my box. On A6000 with MLX, I saw basically the same behavior. The main thing that moved was latency, not quality. That matches what I was seeing. The pattern around continuous batching has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable. |
|
« Next Oldest | Next Newest »
|