+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: LLM Models (https://www.datasculpting.ai/inference/forumdisplay.php?fid=12)
+--- Forum: Proprietary / Frontier (https://www.datasculpting.ai/inference/forumdisplay.php?fid=48)
+--- Thread: where open models feel surprisingly good (/showthread.php?tid=921)
Pages:
1
2
Re: where open models feel surprisingly good - batchcraft - 10-18-2026
What worked for me was pretty simple. If you're on TensorRT-LLM, 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.
Re: where open models feel surprisingly good - cacheplane98 - 10-19-2026
Good point. That matches what I saw on 7900 XTX.
Re: where open models feel surprisingly good - mlxgarden - 10-19-2026
Interesting, I hadn't tried that. That matches what I saw on A6000.
Re: where open models feel surprisingly good - deltagrid - 10-19-2026
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at long context. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.