I ran the Qwen3 235B Q3 precision in LM studio on DGX Spark, it was fine initially but then I noticed that the system would take up 20 GB of memory space doing nothing (or I believe nothing), and then I could not load the 103 GB size AI model due to lack of memory space. Does any one know how to cl…

In addition to the reply above, you may still not be able to run it as you need some RAM for KV cache and other buffers. You can try to clear caches and switch OS to multiuser (text only) mode to save some RAM on not loading the GUI, but it may still not be enough.

Whats the lowest memory before loading anything in spark ? And why cache is using such large memory ?

It’s a filesystem cache. Linux principle is free memory is wasted memory, so it aggressively caches stuff so it works faster. Normally it’s not a problem, but there is a bug in CUDA that doesn’t consider cache in free memory calculation. IOW, instead of using “available memory” it uses “free memory”…

Is that always going to be the case? Are there any efforts to address it in cuda? I noticed that vLLM containers will download a model causing most of the memory to appear in use. Then they fail to launch the model because the download filled the memory up and because vLLM check memory before launc…

I hope NVIDIA fixes it at some point. For now, the workaround is to download models first, flush the caches, then run the models. Not all apps are affected, llama.cpp works just fine without cache flush.

Thanks a lot, guys. Problem solved: as long as I clear the cache with sudo sh -c 'sync; echo 3 > /proc/sys/vm/drop_caches' right before loading the 256 B model with Q3 precision, it works fine with a 30k tokens context window. Good enough for me! Maybe a second DGX if funding secured LOL.

What kind of performance are you getting out of it?

2.5 tokens per second for the response.

My bad: 2.5 tps is from Hermes 70B. Qwen3 235B Q3 was 12 tps

The DGX system itself takes up 20GB memory?

Accelerated Computing DGX Spark / GB10 User Forum DGX Spark / GB10

aniculescu November 6, 2025, 10:32pm 2

Please check out our FAQ on how to clear your cache DGX Spark / GB10 FAQ

Topic		Replies	Views
Dgx spark can only use 119GB of memory running ComfyUI, so it is killed, isn't there 128GB of memory, why can't it be used? DGX Spark / GB10	3	481	December 4, 2025
What is the RAM value shown on the DGX Dashboard? It doesn't seem to match `free` DGX Spark / GB10	7	477	November 19, 2025
Memory Creep on DGX Spark: Where Your 128 GB Actually Goes (And How to Stop It) DGX Spark / GB10 jetson , nemotron	2	649	March 30, 2026
My DGX Spark Hangs ... is this normal? DGX Spark / GB10 Projects llm , dgx	4	295	April 13, 2026
Difference in Total VRAM available for different Sparks DGX Spark / GB10	13	776	April 17, 2026
DGX Spark memory not released using llama.cpp? DGX Spark / GB10 llama	10	242	March 20, 2026
DGX Spark GB10 shows only ~56GB VRAM inside AI Workbench (128GB expected) DGX Spark / GB10	8	1146	December 30, 2025
DGX Dashboard metrics DGX Spark / GB10	6	779	October 27, 2025
DGX Spark stability / out of RAM / overheating DGX Spark / GB10 llama	26	917	May 12, 2026
Is transient freezing expected behavior? DGX Spark / GB10	8	508	November 19, 2025

The DGX system itself takes up 20GB memory?

Related topics