Jetson orin nano hitting system throttled due to over current

Respected community members,

i bought Jetson orin nano last week, whenever i select MAXN super power mode and run a simple ollama with llama3.2:3b even a hello command triggers the system throttled due to over current alert.

Im basically trying to follow a youtube tutorial where the author takes us through the steps with his jetson nano and we can see that they are not hitting this error. Can anyone help me understand if its a hardware problem.

Tutorials trying to follow (both the below video’s shows no alert when running MAXN super)

Any help is appreciated

1 Like

*** Please note that this reply is generated by LLM automatically ***

I’d be happy to help you troubleshoot the issue with your Jetson Orin Nano.

Firstly, congratulations on purchasing the Jetson Orin Nano, a powerful AI computing platform. It’s great that you’re trying to follow YouTube tutorials to get started with your device.

The issue you’re facing is related to the MAXN super power mode, which is a predefined power mode that allows a maximum number of cores and clock frequency for CPU, GPU, DLA, PVA, and SOC engines. When you select this mode and run a simple application like Ollama, you’re encountering a system throttled due to over-current alert.

To help you understand the issue, let’s break it down:

  1. MAXN mode: This mode is designed to provide maximum performance, but it also requires more power. When you select this mode, the system is configured to run at a higher clock frequency, which can lead to increased power consumption.
  2. Over-current alert: This alert is triggered when the system detects that the current drawn by the device exceeds the recommended limit. This can happen when the device is running at a high clock frequency, and the power supply is not able to provide enough current.

Now, let’s compare your situation with the YouTube tutorials you’re trying to follow:

  • The authors in the tutorials are using the same Jetson Orin Nano device, but they’re not encountering the over-current alert.
  • It’s possible that the authors are using a different power supply or configuration that allows their device to run at a higher clock frequency without triggering the over-current alert.

To troubleshoot the issue, you can try the following:

  1. Check your power supply: Ensure that your power supply is capable of providing enough current to the device. You can check the power supply specifications to see if it meets the recommended requirements for the Jetson Orin Nano.
  2. Adjust your power configuration: You can try adjusting your power configuration to reduce the clock frequency or the number of cores used. This might help reduce the power consumption and prevent the over-current alert.
  3. Use a different power mode: You can try using a different power mode, such as the “10W” mode, which is a more power-efficient mode. This might help reduce the power consumption and prevent the over-current alert.
  4. Check for hardware issues: If none of the above steps help, it’s possible that there’s a hardware issue with your device. You can try contacting NVIDIA support or a authorized service provider to diagnose and repair any hardware issues.

In summary, the issue you’re facing is likely related to the power configuration and the power supply. By adjusting your power configuration or using a different power mode, you might be able to resolve the issue. If the problem persists, it’s possible that there’s a hardware issue that needs to be addressed.

I hope this helps! If you have any further questions or need more assistance, feel free to ask.

*** Please give the thumbs up if you get answers you like. Or provide feedback to help us improve the answer. ***

1 Like

Hi @carolyuu ,

im using the same power supply that came with the kit. I captured some logs from PowerGUI can you have a look
logs.zip (6.2 KB)

Regards
Arun Varghese

1 Like

Hi arunodhayam89,

Are you using the devkit or custom board for Orin Nano?
What’s the Jetpack version in use?

Please share the results of the following commands on your board.

$ cat /etc/nv_tegra_release
$ cat /etc/nv_boot_control.conf

$ sudo su
# nvpmodel -q --verbose

And also, the following command when you hit the OC event.

# grep "" /sys/class/hwmon/hwmon*/oc*

You can also provide the dmesg and /etc/nvpmodel.conf for further check.

arunvarghese@arunvarghese-desktop:~$ cat /etc/nv_tegra_release

R36 (release), REVISION: 4.4, GCID: 41062509, BOARD: generic, EABI: aarch64, DATE: Mon Jun 16 16:07:13 UTC 2025

KERNEL_VARIANT: oot

TARGET_USERSPACE_LIB_DIR=nvidia
TARGET_USERSPACE_LIB_DIR_PATH=usr/lib/aarch64-linux-gnu/nvidia
arunvarghese@arunvarghese-desktop:~$ cat /etc/nv_boot_control.conf
TNSPEC 3767-300-0005-T.1-1-0-jetson-orin-nano-devkit-super-
COMPATIBLE_SPEC 3767–0005–1–jetson-orin-nano-devkit-super-
TEGRA_BOOT_STORAGE mmcblk0
TEGRA_CHIPID 0x23
TEGRA_OTA_BOOT_DEVICE /dev/mtdblock0
TEGRA_OTA_GPT_DEVICE /dev/mtdblock0

root@arunvarghese-desktop:/home/arunvarghese# nvpmodel -q --verbose
NVPM VERB: Config file: /etc/nvpmodel.conf
NVPM VERB: parsing done for /etc/nvpmodel.conf
NVPM VERB: Current mode: NV Power Mode: MAXN_SUPER
2
NVPM VERB: PARAM CPU_ONLINE: ARG CORE_0: PATH /sys/devices/system/cpu/cpu0/online: REAL_VAL: 1 CONF_VAL: 1
NVPM VERB: PARAM CPU_ONLINE: ARG CORE_1: PATH /sys/devices/system/cpu/cpu1/online: REAL_VAL: 1 CONF_VAL: 1
NVPM VERB: PARAM CPU_ONLINE: ARG CORE_2: PATH /sys/devices/system/cpu/cpu2/online: REAL_VAL: 1 CONF_VAL: 1
NVPM VERB: PARAM CPU_ONLINE: ARG CORE_3: PATH /sys/devices/system/cpu/cpu3/online: REAL_VAL: 1 CONF_VAL: 1
NVPM VERB: PARAM CPU_ONLINE: ARG CORE_4: PATH /sys/devices/system/cpu/cpu4/online: REAL_VAL: 1 CONF_VAL: 1
NVPM VERB: PARAM CPU_ONLINE: ARG CORE_5: PATH /sys/devices/system/cpu/cpu5/online: REAL_VAL: 1 CONF_VAL: 1
NVPM VERB: PARAM FBP_POWER_GATING: ARG FBP_PG_MASK: PATH /sys/devices/platform/gpu.0/fbp_pg_mask: REAL_VAL: 2 CONF_VAL: 2
NVPM VERB: PARAM TPC_POWER_GATING: ARG TPC_PG_MASK: PATH /sys/devices/platform/gpu.0/tpc_pg_mask: REAL_VAL: 240 CONF_VAL: 240
NVPM VERB: PARAM GPU_POWER_CONTROL_ENABLE: ARG GPU_PWR_CNTL_EN: PATH /sys/devices/platform/gpu.0/power/control: REAL_VAL: auto CONF_VAL: on
NVPM VERB: PARAM CPU_A78_0: ARG MIN_FREQ: PATH /sys/devices/system/cpu/cpu0/cpufreq/scaling_min_freq: REAL_VAL: 729600 CONF_VAL: 729600
NVPM VERB: PARAM CPU_A78_0: ARG MAX_FREQ: PATH /sys/devices/system/cpu/cpu0/cpufreq/scaling_max_freq: REAL_VAL: 1728000 CONF_VAL: 9223372036854775807
NVPM VERB: PARAM CPU_A78_1: ARG MIN_FREQ: PATH /sys/devices/system/cpu/cpu1/cpufreq/scaling_min_freq: REAL_VAL: 729600 CONF_VAL: 729600
NVPM VERB: PARAM CPU_A78_1: ARG MAX_FREQ: PATH /sys/devices/system/cpu/cpu1/cpufreq/scaling_max_freq: REAL_VAL: 1728000 CONF_VAL: 9223372036854775807
NVPM VERB: PARAM CPU_A78_2: ARG MIN_FREQ: PATH /sys/devices/system/cpu/cpu2/cpufreq/scaling_min_freq: REAL_VAL: 729600 CONF_VAL: 729600
NVPM VERB: PARAM CPU_A78_2: ARG MAX_FREQ: PATH /sys/devices/system/cpu/cpu2/cpufreq/scaling_max_freq: REAL_VAL: 1728000 CONF_VAL: 9223372036854775807
NVPM VERB: PARAM CPU_A78_3: ARG MIN_FREQ: PATH /sys/devices/system/cpu/cpu3/cpufreq/scaling_min_freq: REAL_VAL: 729600 CONF_VAL: 729600
NVPM VERB: PARAM CPU_A78_3: ARG MAX_FREQ: PATH /sys/devices/system/cpu/cpu3/cpufreq/scaling_max_freq: REAL_VAL: 1728000 CONF_VAL: 9223372036854775807
NVPM VERB: PARAM CPU_A78_4: ARG MIN_FREQ: PATH /sys/devices/system/cpu/cpu4/cpufreq/scaling_min_freq: REAL_VAL: 729600 CONF_VAL: 729600
NVPM VERB: PARAM CPU_A78_4: ARG MAX_FREQ: PATH /sys/devices/system/cpu/cpu4/cpufreq/scaling_max_freq: REAL_VAL: 1728000 CONF_VAL: 9223372036854775807
NVPM VERB: PARAM CPU_A78_5: ARG MIN_FREQ: PATH /sys/devices/system/cpu/cpu5/cpufreq/scaling_min_freq: REAL_VAL: 729600 CONF_VAL: 729600
NVPM VERB: PARAM CPU_A78_5: ARG MAX_FREQ: PATH /sys/devices/system/cpu/cpu5/cpufreq/scaling_max_freq: REAL_VAL: 1728000 CONF_VAL: 9223372036854775807
NVPM VERB: PARAM GPU: ARG MIN_FREQ: PATH /sys/devices/platform/17000000.gpu/devfreq_dev/min_freq: REAL_VAL: 306000000 CONF_VAL: 0
NVPM VERB: PARAM GPU: ARG MAX_FREQ: PATH /sys/devices/platform/17000000.gpu/devfreq_dev/max_freq: REAL_VAL: 1020000000 CONF_VAL: 9223372036854775807
NVPM VERB: PARAM GPU_POWER_CONTROL_DISABLE: ARG GPU_PWR_CNTL_DIS: PATH /sys/devices/platform/gpu.0/power/control: REAL_VAL: auto CONF_VAL: auto
NVPM VERB: PARAM EMC: ARG MAX_FREQ: PATH /sys/kernel/nvpmodel_clk_cap/emc: REAL_VAL: 3199000000 CONF_VAL: 9223372036854775807

grep “” /sys/class/hwmon/hwmon*/oc*
/sys/class/hwmon/hwmon2/oc1_event_cnt:0
/sys/class/hwmon/hwmon2/oc1_throt_en:1
/sys/class/hwmon/hwmon2/oc2_event_cnt:0
/sys/class/hwmon/hwmon2/oc2_throt_en:1
/sys/class/hwmon/hwmon2/oc3_event_cnt:21628
/sys/class/hwmon/hwmon2/oc3_throt_en:1

It seems you hit the OC3 event which means the instant high power.

It may be caused from you are running this application.
Please note that MAXN is an unconstraint power mode rather than best performance mode. We would suggest you create a custom power mode configuration according to your use case to achieve the best performance w/o hitting OC event.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.