benchmarks that map to real use

[routeline23]

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

Maybe useful as a starting point: Ollama on 7900 XTX, keeping reranking in mind from the start.

Maybe useful as a starting point for newer folks.

I care more about stability than squeezing the last possible tokens/sec out of it.

[kernelhouse70]

Appreciate the detail. That matches what I saw on GB200. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[mlxgarden]

Thanks, that helps. I don't think your conclusion is far off.

[promptfield]

Good point. I ended up in about the same place using vLLM. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[vramforge]

I'd start with the simpler stack.

[vrambandit]

Thanks, that helps. That matches what I saw on M3 Max. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[torchstation]

My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at INT4. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[vrambandit]

My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at INT4. A lot of these threads

subscribed, curious where this lands.

[cacheline]

worth checking the driver first.

[orbitline]

What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tail latency. Once you know the plain path works, then add the faster path back in piece by piece.