Your laptop runs the model on the integrated GPU, not the RTX

nvidia-smi shows the GPU idle while the model runs

Written by Jakub Rusinowski

The error

+-----------------------------------------+
| Processes:                              |
|  GPU   PID   Type   Process name   Usage |
|=========================================|
|  No running processes found              |
+-----------------------------------------+

1. 1

   Set the Windows graphics preference — for the terminal as well as the app

   Go to Settings → System → Display → Graphics, add the executable, choose Options → High performance. Do this for the inference binary (ollama.exe, LM Studio, or the python.exe inside your virtual environment) and for the terminal host you launch it from — WindowsTerminal.exe, powershell.exe, or Code.exe. The second half is the step people miss, and it is usually the one that actually changes the outcome, because the child process inherits the parent's preference.

   PowerShellCopy

   # PowerShell — the full paths you will need to browse to
   (Get-Command ollama).Source
   where.exe python
   (Get-Process WindowsTerminal -ErrorAction SilentlyContinue).Path

   Did it work?Close the terminal, open a new one, start a generation and watch. The dGPU should now show a process and non-zero utilisation.

   PowerShellCopy

   nvidia-smi --query-compute-apps=pid,process_name,used_memory --format=csv

2. 2

   Set the NVIDIA Control Panel preference too

   NVIDIA Control Panel → Manage 3D Settings. On the Global Settings tab set *Preferred graphics processor* to High-performance NVIDIA processor, and on Program Settings add the same executables. This is a separate mechanism from the Windows setting, not a duplicate of it, and on some driver versions it is the one that takes effect. Setting both is not redundant — it removes a variable.

   Did it work?The Program Settings tab should list your executable with the NVIDIA processor selected. Then re-run the check from fix 1.

   PowerShellCopy

   nvidia-smi dmon -c 10

3. 3

   Check for a BIOS MUX or hybrid-graphics mode

   Many gaming laptops expose a firmware setting — variously MUX switch, Graphics Mode, Hybrid / Discrete, or Advanced Optimus — that decides at the hardware level which GPU drives the display and which is available. It overrides both software settings above. Set to Discrete or dGPU-only, the integrated chip is out of the picture entirely and this whole class of problem disappears; the cost is battery life, and the change usually needs a reboot. Vendor utilities (Armoury Crate, Lenovo Vantage, Alienware Command Center) often expose the same switch without a BIOS trip.

   Careful: Changing graphics mode in firmware can leave you at a blank screen on the next boot if the panel is wired to the other GPU. Know how to clear CMOS or boot into safe mode on your model before you change it.
4. 4

   Plug the laptop in, and check the vendor power policy

   Several vendors disable or heavily throttle the discrete GPU on battery, and some do it silently. If speed is fine on mains and poor unplugged, that is the mechanism rather than anything you have misconfigured. Check Windows' own power mode as well — Settings → System → Power & battery → Power mode set to *Best power efficiency* biases the whole system toward the iGPU. Sustained inference is a heavy continuous load and is not a battery workload in any case.

   PowerShellCopy

   # PowerShell — on mains or on battery, and what power scheme is active?
   (Get-CimInstance -ClassName Win32_Battery).BatteryStatus  # 2 = on AC power
   powercfg /getactivescheme

5. 5

   Pin the GPU explicitly with CUDA_VISIBLE_DEVICES, by UUID

   Once the dGPU is available to the process, you can name it directly. Use nvidia-smi -L to list devices and prefer the UUID over the numeric index — indices are assigned by enumeration order and can change across reboots, driver updates, or when an eGPU is attached, so a config pinned to 0 silently points somewhere else one morning. Remember that setting this to a device that does not exist forces CPU inference, which is a different symptom on a nearby page.

   PowerShellCopy

   # PowerShell — list devices with their UUIDs
   nvidia-smi -L
   # GPU 0: NVIDIA GeForce RTX 4060 Laptop GPU (UUID: GPU-1a2b3c4d-...)
   
   # Pin by UUID for this session
   $env:CUDA_VISIBLE_DEVICES="GPU-1a2b3c4d-..."
   ollama serve

   Did it work?The chosen card shows the inference process and rising memory use while a model is loaded.

   PowerShellCopy

   nvidia-smi --query-compute-apps=process_name,used_memory --format=csv

6. 6

   Be honest about whether the dGPU is big enoughMost common fix

   Worth checking before you spend an evening on graphics preferences: laptop discrete GPUs are often 4 to 8 GB, and laptop variants of a desktop card can carry less memory and less bandwidth than the name suggests. If your RTX has 6 GB, a 7B model at Q4 fits and an 8B at Q5 does not, and forcing the dGPU will not change that arithmetic. Check the model against the card's real VRAM — if it does not fit, a smaller model on the right GPU beats a large model spilling to system RAM.

   PowerShellCopy

   # PowerShell — the real numbers for the card in this laptop
   nvidia-smi --query-gpu=name,memory.total,memory.used --format=csv

   Check what fits your hardwarecheck which models fit a 6 or 8 GB laptop GPUOpen the VRAM checker →