best local open-weight model this week: anyone testing this?

[dockworks23]

Thought I'd post a small recipe because a lot of threads ask similar things.

Just sharing a setup that ended up working reasonably well: FLUX, TensorRT-LLM, mini PC, with a lot of attention on tail latency.

Maybe useful as a starting point for newer folks.

[orbitbench6]

What worked for me was pretty simple. If you're on Ollama, 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.

[papermixer4]

worth checking the driver first.

[vectorhouse71]

worth checking the driver first.

[southtinker]

Can you fill in a bit more context? Are you testing this on B200 or something else?

[dockworks23]

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.

[bytelab]

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 gl

I'd start with the simpler stack.

[kernelghost]

[quote]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.

I hit almost the same issue last night.

[vectorpoint]

What worked for me was pretty simple. On M3 Max, the easiest win is often to back off the aggressive settings and see whether the problem survives.

[fusedhall56]

Good point. That matches what I saw on dual 3090. The biggest change for me was simplifying the stack instead of adding one more optimization layer.