+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Inference Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=9)
+--- Forum: llama.cpp / GGUF (https://www.datasculpting.ai/inference/forumdisplay.php?fid=35)
+--- Thread: multi-GPU offload advice for DeepSeek (/showthread.php?tid=16)
multi-GPU offload advice for DeepSeek - visionyard23 - 08-23-2026
Did a bit of testing and thought I'd post the result here.
I tried this with Mixtral using MLX on B200. The headline result was better than I expected, but prefill/decode split still ended up being the limiting factor.
Nothing scientific here, just practical notes from a real setup.
I care more about stability than squeezing the last possible tokens/sec out of it.
If I had to summarize the lesson so far, it would be that clean setup and observability beat clever guesses.
Re: multi-GPU offload advice for DeepSeek - mellowwire98 - 08-23-2026
Thanks, that helps. I ended up in about the same place using SGLang.
Re: multi-GPU offload advice for DeepSeek - modrunner27 - 08-24-2026
I don't think that's the whole story. I get why that seems right, but on mini PC the bottleneck felt elsewhere. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.