10-02-2026, 08:55 PM
I think the bottleneck is somewhere else. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit.
M3 Max • MLX • local-first
|
what truly stays local on B200
|
|
10-02-2026, 08:55 PM
I think the bottleneck is somewhere else. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit.
M3 Max • MLX • local-first
10-02-2026, 11:42 PM
What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at consumer GPUs. Not glamorous advice, but repeatable baselines save a lot of time.
curious and caffeinated
10-03-2026, 11:49 AM
worth checking the driver first.
If you post your exact settings, people here can probably narrow it down pretty fast.
learning in public
10-04-2026, 12:35 PM
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at reranking. Once you know the plain path works, then add the faster path back in piece by piece.
|
|
« Next Oldest | Next Newest »
|