![]() |
|
tools worth paying for with MLX - Printable Version +- Inference (https://www.datasculpting.ai/inference) +-- Forum: Apps / Utilities / Tools (https://www.datasculpting.ai/inference/forumdisplay.php?fid=18) +--- Forum: Online / Hosted (https://www.datasculpting.ai/inference/forumdisplay.php?fid=19) +--- Thread: tools worth paying for with MLX (/showthread.php?tid=633) |
tools worth paying for with MLX - batchshed - 10-01-2026 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: DeepSeek, SGLang, 5090, with a lot of attention on structured output. Maybe useful as a starting point for newer folks. At this point the real bottleneck is my patience. Re: tools worth paying for with MLX - bytelab - 10-02-2026 That matches what I was seeing. The pattern around tokens/sec has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer. Re: tools worth paying for with MLX - modrunner27 - 10-02-2026 Quote:That matches what I was seeing. The pattern around tokens/sec has been pretty similar for me. The biggest change for me was simplifying the stack inst Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed up before throughput collapsed. Re: tools worth paying for with MLX - mangopeak72 - 10-02-2026 I don't think that's the whole story. I've seen people blame KV cache pressure when the real issue was much more mundane. Re: tools worth paying for with MLX - tinycontext - 10-02-2026 Quote:I don't think that's the whole story. I've seen people blame KV cache pressure when the real issue was much more mundane. I hit almost the same issue last night. Re: tools worth paying for with MLX - vramarch - 10-05-2026 Good point. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable. Re: tools worth paying for with MLX - mangopeak72 - 10-08-2026 following this because I'm in the same boat. Re: tools worth paying for with MLX - dockworks23 - 10-08-2026 worth checking the driver first. Re: tools worth paying for with MLX - deepseeked - 10-11-2026 Quote:worth checking the driver first. Need a little more detail here. Is this local-only or are you routing anything externally? |