+- 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: 70B still worth the pain with MLX (/showthread.php?tid=53)
70B still worth the pain with MLX - embershed99 - 08-28-2026
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: FLUX, Ollama, 7900 XTX, with a lot of attention on tool calling.
If someone wants the exact settings I can clean them up and post them.
I care more about stability than squeezing the last possible tokens/sec out of it.
Re: 70B still worth the pain with MLX - sanepeak48 - 08-30-2026
worth checking the driver first.
Re: 70B still worth the pain with MLX - turbosupply83 - 08-30-2026
What worked for me was pretty simple. If you're on LM Studio, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.