Received Jetson Nano Orin Super less than one day ago (1/5/2025).
Running Jetpack 6.1 rev 1 36.4.2. When trying to do some AI, ollama and anythingLLM in MAXN mode, it throttled down to 7W and says CV0, CV1 and CV2 “offline” (jtop and Jetson Power GUI). 68 degree F room. I have read "System throttled due to Over-current." but do not see a way to remove this “offline” error. I can not use MAXN without a red bang (!) icon. Thanks for any suggestions.
Hi,
Which nvpmodel do you use?
It’s expected to use mode 2 with jetson_clocks to fix the clocks to the maximum.
Would you mind sharing the output of tegrastats with us as well?
Thanks.
Thanks for the reply. Answers below. Let me know if you need anything else.
Using 0:15 W, but would like to use 2:MAXN, however that errors out, and throttles down to 1:7 W. Most likely because of the CV0, CV1 and CV2 sensors stuck on “Offline”.
tegrastats
01-07-2025 06:18:23 RAM 3050/7620MB (lfb 85x2MB) SWAP 1327/3810MB (cached 4MB) CPU [10%@729,12%@729,7%@729,11%@729,4%@729,9%@729] GR3D_FREQ 31% cpu@48.687C soc2@47.906C soc0@49.218C gpu@49.625C tj@50.437C soc1@50.437C VDD_IN 5920mW/5920mW VDD_CPU_GPU_CV 878mW/878mW VDD_SOC 1837mW/1837mW
$ 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: 15W 0
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: 1497600 CONF_VAL: 1497600
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: 1497600 CONF_VAL: 1497600
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: 1497600 CONF_VAL: 1497600
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: 1497600 CONF_VAL: 1497600
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: 1497600 CONF_VAL: 1497600
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: 1497600 CONF_VAL: 1497600
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: 612000000 CONF_VAL: 612000000
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: 2133000000 CONF_VAL: 2133000000
Hi,
Please run the tegrastats with sudo so more info can be collected.
The super mode should be 25W with the CPU clock at 1.7GHz but it looks like your is less.
Here is the command to set Orin Nano into Super mode:
$ sudo nvpmodel -m 2
$ sudo jetson_clocks
Then please double-check the clock to see if the CPU reaches 1.7 GHz and GPU is ~1,020 MHz.
... CPU [0%@1728,0%@1728,0%@1728,0%@1728,1%@1728,0%@1728] EMC_FREQ 1%@3199 GR3D_FREQ 0%@[1019] ...
You can find more info about Super mode in the below post:
Thanks.
Once again, thanks for the reply. After performing your suggestions, cv0, cv1 and cv2 still “Offline” Simple ollama “good morning” get a red ! in the upper right next to MAXN. The important part to me is the constant “Offline” error for the sensors. Thanks in advance for any suggestions.
Sudo tegrastats
sudo nvpmodel -m 2
sudo jetson_clocks
Nothing happens after sudo jetson_clocks. The sudo npmodel -m 2 does change the power level to MAXN.
tegrastats output:
01-08-2025 08:57:40 RAM 1847/7620MB (lfb 4x4MB) SWAP 0/3810MB (cached 0MB) CPU [0%@1728,2%@1728,0%@1728,1%@1728,1%@1728,0%@1728] EMC_FREQ 0%@3199 GR3D_FREQ 0%@[1019] NVDEC off NVJPG off NVJPG1 off VIC off OFA off APE 200 cpu@46.937C soc2@45.875C soc0@47.156C gpu@47.75C tj@47.968C soc1@47.968C VDD_IN 7627mW/5812mW VDD_CPU_GPU_CV 1632mW/774mW VDD_SOC 2711mW/1883mW
after ollama “good morning” tegrastats output:
01-08-2025 09:01:32 RAM 5504/7620MB (lfb 2x4MB) SWAP 14/3810MB (cached 0MB) CPU [6%@1728,5%@1728,7%@1728,2%@1728,2%@1728,1%@1728] EMC_FREQ 1%@3199 GR3D_FREQ 0%@[1019] NVDEC off NVJPG off NVJPG1 off VIC off OFA off APE 200 cpu@52.406C soc2@51.687C soc0@52.5C gpu@53.031C tj@53.937C soc1@53.937C VDD_IN 7854mW/7017mW VDD_CPU_GPU_CV 1791mW/1358mW VDD_SOC 2711mW/2401mW
Hi,
Thanks for the update.
We are checking this with our internal team. Will provide more info to you soon.
I think I have the identical problem! cv0 , cv1 , cv2 All offline
sudo tegrastats:
01-10-2025 10:59:15 RAM 3843/7620MB (lfb 20x4MB) SWAP 245/3810MB (cached 0MB) CPU [2%@1728,2%@1728,2%@1728,1%@1728,0%@1728,1%@1728] EMC_FREQ 0%@3199 GR3D_FREQ 0%@[1019] NVDEC off NVJPG off NVJPG1 off VIC off OFA off APE 200 cpu@49.437C soc2@47.875C soc0@49.125C gpu@49.687C tj@49.687C soc1@49.5C VDD_IN 7829mW/7834mW VDD_CPU_GPU_CV 1706mW/1706mW VDD_SOC 2821mW/2790mW
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
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: 1728000 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: 1728000 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: 1728000 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: 1728000 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: 1728000 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: 1728000 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: 1020000000 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
also no response to sudo jetson_clocks
“Warning System Throttled due to overcurrent” on a simple text only request to ollama
Any suggestions appreciated
1 Like
After a while throttling ceases and the the system returns to MAXN profile , howver still with cv0, cv1 and cv2 offline.
Adding that I also am experiencing the same behavior.
Thanks for all the “me too” messages.
I booted with the old jetpack original microSD (no added software) and the cv0, cv1, and cv2 “offline” errors are there. Hope this helps.
I removed and re-seated the Jetson Orin Nano module into the carrier board. Didn’t help; cv0, cv1, and cv2 “offline” errors still there. Hope this helps.
Hi, all
Thanks for sharing the testing results.
We are still checking this with our internal team. Will get back to you later.
Thanks.
Hi, all
Thanks for your patience.
The CV0, CV1, and CV2 offline on Orin Nano are expected and not a bug.
CV0, 1 refers to DLA0, DLA1 temperature, and CV2 refers to PVA temperature.
Since Orin Nano doesn’t have DLA and PVA, it’s expected to see it shown as “offline”.
Thanks.
Thanks for finding that out. This suggests the overcurrent throttling is not related to CV0/1/2 being offline, but it does not address the issue itself. Is this something that is also being looked into?
As OP is reporting, I am also having the issue in that a heavy workload in maxn power mode causes the system to instantly throttle, though mine is to about 11w. I can maintain the same workload at 15w just fine, however.
1 Like
Similarly, thanks.
But my system was working quite nicely without the “offline” error, not throttling back and not getting a red bang message in the upper right corner. Then something happened and the error was recieved, without going away. Now, I cannot use the computer as it previously performed.
The error is permanent. “Offline” is permanent, as far as I can see it is dramatically affecting performance, and not being fixed by this discussion yet. This is NOT a feature.
Hope this continues to help.
Hi,
We want to reproduce this issue locally to gather more info.
Could you share the detailed steps (like running ollama) to hit this issue?
Thanks.
In the interest of expedience and as this is a pretty simple scenario I’ll share mine given that it’s almost certainly the same as the thread starter.
-
Set power mode to maxn (how this is done hasn’t mattered for me)
-
In Terminal, run any model in Ollama and ask it a question.
It’s that simple, the system will show the overcurrent message almost instantly.
Doing the same in15w power mode is fine, however.
1 Like
Yes, same for me just for clarity I am running gemma2:2b which is 1.6GB in size.
There is plenty of memory available, but get the over-current warning and the red bang everytime.
It seems to be when ollama first hits the gpu.
1 Like
Here is what I did to solve this:
Change GPU MAX_FREQ -1 to 900000000 in the MAXN power profile
Which is close to the maximum which i believe is 921 Mhz
in /etc/nvpmodel.conf
< POWER_MODEL ID=2 NAME=MAXN >
CPU_ONLINE CORE_0 1
CPU_ONLINE CORE_1 1
CPU_ONLINE CORE_2 1
CPU_ONLINE CORE_3 1
CPU_ONLINE CORE_4 1
CPU_ONLINE CORE_5 1
FBP_POWER_GATING FBP_PG_MASK 2
TPC_POWER_GATING TPC_PG_MASK 240
GPU_POWER_CONTROL_ENABLE GPU_PWR_CNTL_EN on
CPU_A78_0 MIN_FREQ 729600
CPU_A78_0 MAX_FREQ -1
CPU_A78_1 MIN_FREQ 729600
CPU_A78_1 MAX_FREQ -1
CPU_A78_2 MIN_FREQ 729600
CPU_A78_2 MAX_FREQ -1
CPU_A78_3 MIN_FREQ 729600
CPU_A78_3 MAX_FREQ -1
CPU_A78_4 MIN_FREQ 729600
CPU_A78_4 MAX_FREQ -1
CPU_A78_5 MIN_FREQ 729600
CPU_A78_5 MAX_FREQ -1
GPU MIN_FREQ 0
GPU MAX_FREQ 900000000
GPU_POWER_CONTROL_DISABLE GPU_PWR_CNTL_DIS auto
EMC MAX_FREQ -1