When loading a large model like gpt-oss-120b, about 80% of the way loading, the system will freeze and be unresponsive. The mouse cursor won’t move and if you have any animations in Firefox in the background, they also stall. After 15-20 seconds, it keeps going. (This is with 65K context window i…

Hi Alan, can you share the exact steps/frameworks you are loading and running inference on gpt-oss-120b? We want to see if we can locally repro and fix if necessary.

For LMStudio freeze and resume Load LM-Studio-0.3.30-2-arm64.AppImage Load official openai/gpt-oss-120b model context length 65536 GPU offload 36/36 CPU Threads 18 Offload KV Cache to GPU Memory (yes) Keep Model in Memory (no) Seed 94121 Custom Fields (High Reasoning Effort) Runtime: CUDA …

Hi Alan, I don’t see any issue with your DDR. While we work on reproducing your exact scenario, I wanted to share a best practice we recommend: clearing the cache before starting any Docker container. For example: [image] Build a Video Search and Summarization (VSS) Agent | DGX Spark R…

[13786.069340] NVRM: nvCheckOkFailedNoLog: Check failed: Out of memory [NV_ERR_NO_MEMORY] (0x00000051) returned from _memdescAllocInternal(pMemDesc) @ mem_desc.c:1359 [13869.129129] NVRM: nvCheckOkFailedNoLog: Check failed: Out of memory [NV_ERR_NO_MEMORY] (0x00000051) returned from _memdescAllocIn…

Thanks for the quick Response Alan. I believe the kernel log level is set to quiet and therefore you are not seeing the OOM Killer prints in the log. Can you increase the log level using below command and then share the log. dmesg -n 8 Or after reproduction, do a dmesg and share the log. Anoth…

Last night, I got two OOM errors with the pause in responsiveness, cleared the cache (which you see) and reloaded, and got no pause in responsiveness other than a stutter, and it generated the OOM error. TODAY, I did sudo dmesg -n 8. Dropped the cache first, and then loaded gpt-oss-120b. Didn’t l…

Did this ever get resolved? I have similar experience, even with context length at default of 4k.

Today’s updates solved this issue. [image] DGX Spark Software Updates Announcements DGX Spark software updates will begin rolling out to all systems starting today. These updates will also apply to partner systems based on the NVIDIA GB10 Grace Blackwell Super…

Is transient freezing expected behavior?

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

ralph.lora November 19, 2025, 6:54pm 9

Today’s updates solved this issue.

Topic		Replies	Views
LM Studio models overload freezes Spark DGX Spark / GB10 dgx-spark-issue	7	497	June 7, 2026
System crashes when memory is full DGX Spark / GB10 dgx-spark-issue	35	2765	June 15, 2026
My DGX Spark Hangs ... is this normal? DGX Spark / GB10 Projects llm , dgx	5	791	July 15, 2026
[Fixed] DGX Spark freezing and lockup issue; unable to load new models due to cache saturation DGX Spark / GB10	1	110	June 16, 2026
DGX Spark stability / out of RAM / overheating DGX Spark / GB10 llama , dgx-spark-issue	34	2491	July 17, 2026
DGX Spark Shutdown around 95°C during nanoChat Pretraining (20-30 min) DGX Spark / GB10	21	1939	March 23, 2026
The DGX system itself takes up 20GB memory? DGX Spark / GB10 cuda	20	1728	November 23, 2025
LMStudio Error: Cannot obtain free VRAM bytes for GPU0: NVIDIA GB10 DGX Spark / GB10	5	760	December 1, 2025
Memory Creep on DGX Spark: Where Your 128 GB Actually Goes (And How to Stop It) DGX Spark / GB10 jetson , nemotron	2	1332	March 30, 2026
DGX Spark becomes unresponsive (“zombie”) instead of throwing CUDA OOM DGX Spark / GB10	16	1963	April 10, 2026

Is transient freezing expected behavior?

Related topics