09-25-2026, 12:47 AM
Interesting, I hadn't tried that. I ended up in about the same place using llama.cpp. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
|
NVIDIA driver regression with MLX
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
NVIDIA driver regression with MLX - by sparrowkite53 - 09-22-2026, 11:43 PM
Re: NVIDIA driver regression with MLX - by edgecoast - 09-23-2026, 12:16 PM
Re: NVIDIA driver regression with MLX - by amberpatch25 - 09-25-2026, 12:47 AM
|
Users browsing this thread: 1 Guest(s)