best local runtime for mixed models

[vectorhouse71]

[quote]My first guess would be this: If you're on LM Studio, I'd confirm the version first and then reduce variables until the behavior is obvious. A

My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at NVFP4. Not glamorous advice, but repeatable baselines save a lot of time.

[latentscope35]

My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at prefill/decode split. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[modgarden]

I'd start with the simpler stack.

[dockridge]

What worked for me was pretty simple. If you're on MLX, I'd confirm the version first and then reduce variables until the behavior is obvious.

[dockridge]

I tested this tonight. The issue went away once I changed one setting and restarted the stack cleanly.

[orbitbench6]

What worked for me was pretty simple. If you're on PyTorch, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.