[Help] Frequent BSOD with NVIDIA RTX 3060 on Windows 11

[Help] Frequent BSOD with NVIDIA RTX 3060 on Windows 11 – Need Advice - Printable Version

+- Ipoh Community Forums (https://forums.ipoh.com.my)
+-- Forum: Information Technology (https://forums.ipoh.com.my/forum-14.html)
+--- Forum: Computer Hardware (https://forums.ipoh.com.my/forum-15.html)
+--- Thread: [Help] Frequent BSOD with NVIDIA RTX 3060 on Windows 11 – Need Advice (/thread-20025.html)

[Help] Frequent BSOD with NVIDIA RTX 3060 on Windows 11 – Need Advice - silverfish - 10-02-2025

Hello everyone,
I’m facing a persistent issue with my PC and would really appreciate some advice or insights from the community.
System Specifications:

Motherboard: ASUS TUF Gaming B550-PLUS
CPU: AMD Ryzen 5 5600X
GPU: NVIDIA GeForce RTX 3060 (Driver version 551.67)
RAM: 2×16 GB DDR4 3200 MHz
Storage: Samsung 980 Pro 1TB NVMe SSD
PSU: Corsair RM650x (80 Plus Gold)
OS: Windows 11 Pro 23H2 (latest updates installed)

Problem Description:
Whenever I run a heavy game such as Cyberpunk 2077 or Control, my system crashes after about 10–15 minutes with a Blue Screen of Death (BSOD). The error code is “VIDEO_DXGI_FATAL_ERROR”.
Sometimes, the screen freezes briefly before the system restarts. In the Event Viewer, I keep seeing:

Code:
Display driver nvlddmkm stopped responding and has successfully recovered.

What I Have Tried So Far:

Updated NVIDIA drivers (both stable and beta) → issue persists
Stress-tested GPU with FurMark → passed without crashes
Ran MemTest86 on RAM → no errors found
Checked PSU voltages with monitoring tools → stable
Cleaned dust and monitored GPU temperature (max ~78°C) → still BSOD
Disabled background apps and services → no improvement

Questions for the Community:

Could this be caused by a compatibility issue between the GPU driver and Windows 11 updates?
Is there a reliable tool for deeper GPU diagnostics (to check voltage stability or hardware faults)?
Would replacing the GPU be the most practical solution, and if so, what model would you recommend within a ~RM 2000 budget?
If I decide to RMA the card, are there any trusted service centers in Malaysia that you’d suggest?

Any advice, personal experience, or troubleshooting tips would be greatly appreciated. I’ll make sure to update this thread with any progress so it can help others who face a similar issue in the future.
Thanks in advance!
Among Us

RE: [Help] Frequent BSOD with NVIDIA RTX 3060 on Windows 11 – Need Advice - superadmin - 10-02-2025

Could it be due to the over heating of the graphic card?

RE: [Help] Frequent BSOD with NVIDIA RTX 3060 on Windows 11 – Need Advice - superadmin - 10-02-2025

ChatGPT replied:

What the Error Suggests

Code:
VIDEO_DXGI_FATAL_ERROR
usually points to DirectX graphics subsystem problems, most often linked to:
- GPU drivers
- VRAM instability
- Power delivery issues (GPU not getting clean/stable power under load)
- Rarely, a Windows 11 update–driver conflict
The Event Viewer entry “nvlddmkm stopped responding and has successfully recovered” is a TDR (Timeout Detection and Recovery) error, meaning the GPU didn’t respond in time.

⚡ Why It’s Probably Not Overheating

You reported 78°C max under load, which is well within safe limits (RTX 3060 is usually fine up to ~83–85°C before thermal throttling).
If it was strictly thermal, FurMark would have crashed the card too (since FurMark typically pushes GPU temps higher than games).

So overheating is unlikely the root cause here.

✅ Other Possible Causes

Driver Conflict / Windows 11 Update
- Sometimes NVIDIA drivers + certain Win 11 builds cause instability.
- Rolling back to a slightly older stable driver (e.g., 537.58 or 546.33) sometimes resolves this.
Power Delivery Issue
- Your RM650x is a solid PSU, but if the PCIe cable or slot is loose or if the GPU is drawing unstable power under gaming load (which differs from FurMark), it could trigger BSODs.
VRAM Fault / GPU Degradation
- Stress tests like FurMark mainly load shaders, but some games stress VRAM differently.
- A slightly faulty VRAM chip could pass FurMark but crash in real-world workloads.
PCIe Bus / BIOS Settings
- Sometimes forcing PCIe Gen 3 in BIOS (instead of Auto/Gen 4) improves stability on B550 boards with RTX 30 series cards.

? Recommended Next Steps

Clean Driver Reinstall (DDU)
- Use Display Driver Uninstaller (DDU) in Safe Mode.
- Reinstall NVIDIA drivers (try 546.33 or 537.58 — not just the latest).
Check BIOS + Chipset
- Update your ASUS B550 BIOS to the latest.
- Install latest AMD chipset drivers.
Force PCIe Gen 3
- In BIOS: Advanced → PCIe/Link Speed → Set GPU slot to Gen 3.
- Many users report crashes disappearing with this setting.
Test with Underclock
- Use MSI Afterburner to reduce GPU core clock by ~100 MHz and VRAM by ~300 MHz.
- If BSODs stop, the GPU silicon or VRAM is unstable → RMA recommended.
Try Different PSU Cable
- Use a different PCIe power cable (separate rail if modular).
- Reseat GPU in slot.

? Answering Your Questions

Could it be Windows 11 driver conflict?
→ Yes, it’s possible. Try an older NVIDIA driver after a DDU clean install.
Deeper GPU diagnostics?
- Tools: OCCT GPU VRAM test, 3DMark stress test, HWInfo64 (voltage/power draw logs).
- These often reveal VRAM or power instability missed by FurMark.
Replace GPU?
- Only if underclocking + driver rollback + BIOS tweaks don’t help.
- Within RM 2000 (~$400), a RTX 4060 Ti 16GB or RX 7700 XT would be good upgrades.
RMA in Malaysia
- If your GPU is still under warranty, check with your ASUS/NVIDIA authorized distributor (e.g., IdealTech, Tech Armory, or directly through ASUS Malaysia support).

? My gut feeling: not overheating, but likely driver/PCIe compatibility or VRAM instability.
Try the DDU clean reinstall + PCIe Gen 3 setting first — those solve 70% of these RTX 30-series BSOD cases.
Would you like me to walk you step-by-step on how to set your BIOS to PCIe Gen 3 and run a VRAM-specific stress test? That way we can confirm if it’s hardware or software before thinking about RMA.