Hi, I ran one NIM container like this. Works ok, able to access it from Open WebUI via direct connection. docker run -it --rm --name=nim-qwen3-dgx-spark --gpus all --shm-size=16GB -e CORS_ALLOWED_ORIGINS=“*” -e NGC_API_KEY=$NGC_API_KEY -e ACCE PT_NVIDIA_TOS=1 -v “$HOME/.cache/nim:/opt/n…

We just released a software update today that addresses this issue, please make sure to update your systems [image] DGX Spark Software Updates Announcements DGX Spark software updates will begin rolling out to all systems starting today. These updates will also…

Hi, The number on the DGX Dashboard shows the amount of memory being used, not how much is free. The nvidia-smi command is not always entirely accurate due to the unified memory architecture. Please reference our FAQ for more information.

Hi, the FAQ says to use free -h . But the memory in use shown by that command is 93GB but the DGX dashboard shows much lower usage. Why is there a such a big difference? It would be good if the DGX dashboard is improved to show details and is more accurate. [Screenshot 2025-10-21 at 10.13.24 AM]

Hi, This is a known issue that will be fixed in the next update. For now you can also look at /proc/meminfo at the MemAvailable section for the most accurate number.

Issue fixed in previous update, marking as answered

It’s not fixed yet. DGX Dashboard is still showing inflated data for System memory

You may want to clear cache and restart sudo sh -c 'sync; echo 3 > /proc/sys/vm/drop_caches'

Sorry for the early answer, DGX Dashboard will be using /proc/meminfo after the next major update

Any planned date for the update?

Second NIM container won't start due to less than desired GPU memory utilization

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

aniculescu November 19, 2025, 3:58pm 10

We just released a software update today that addresses this issue, please make sure to update your systems

Topic		Replies	Views
Issue with --gpu-memory-utilization — parameter seems ignored Models nim	0	50	April 20, 2026
NVIDIA NIM Container with CUDA out of Memory Problem Docker and NVIDIA Docker cuda , ubuntu , docker , nim , llama3-8b-instruct	2	764	September 20, 2024
NIM LLM Containers Fail on DGX Spark (GB10): Triton/vLLM Crash on sm_121 and NGC Permission Errors DGX Spark / GB10 jetson , nim , llama , nemotron	4	465	February 6, 2026
Issues while starting NIM container in A10 VM Models nim , llama3-8b-instruct	4	268	September 4, 2024
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	500	December 4, 2025
Memory Creep on DGX Spark: Where Your 128 GB Actually Goes (And How to Stop It) DGX Spark / GB10 jetson , nemotron	2	732	March 30, 2026
NIM - Llama3-8b-Instruct - GPU resource usage is very high Models nim , llama3-8b-instruct	0	106	March 12, 2025
My DGX Spark Hangs ... is this normal? DGX Spark / GB10 Projects llm , dgx	4	327	April 13, 2026
The DGX system itself takes up 20GB memory? DGX Spark / GB10 cuda	20	1425	November 23, 2025
Launch the Reranker NIM : Failing to create container for Visual AI Agent nim , llama	9	319	May 23, 2025

Second NIM container won't start due to less than desired GPU memory utilization

Related topics