You are not logged in.
Iam trying to run ollama with my discreet GPU, but ollama is only detecting the CPU.
Packages:
```
pacman -Qs cuda
pacman -Qs nvidia
local/cuda 13.0.2-1
NVIDIA's GPU programming toolkit
local/icu 78.1-1
International Components for Unicode library
local/cuda 13.0.2-1
NVIDIA's GPU programming toolkit
local/egl-gbm 1.1.2.1-1
The GBM EGL external platform library
local/egl-wayland 4:1.1.20-1
EGLStream-based Wayland external platform
local/egl-x11 1.0.3-1
NVIDIA XLib and XCB EGL Platform Library
local/envycontrol 3.5.2-1
CLI tool for Nvidia Optimus graphics mode switching on Linux
local/libnvidia-container 1.18.0-1
NVIDIA container runtime library
local/libvdpau 1.5-3
Nvidia VDPAU library
local/linux-firmware-nvidia 20251111-1
Firmware files for Linux - Firmware for NVIDIA GPUs and SoCs
local/nvidia 580.105.08-2
NVIDIA kernel modules
local/nvidia-container-toolkit 1.18.0-1
NVIDIA container toolkit
local/nvidia-prime 1.0-5
NVIDIA Prime Render Offload configuration and utilities
local/nvidia-utils 580.105.08-2
NVIDIA drivers utilities
local/opencl-nvidia 580.105.08-2
OpenCL implemention for NVIDIA
```
nvidia-smi:
```
nvidia-smi
Fri Nov 14 19:11:10 2025
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 580.105.08 Driver Version: 580.105.08 CUDA Version: 13.0 |
+-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 3050 ... On | 00000000:01:00.0 Off | N/A |
| N/A 39C P8 6W / 20W | 15MiB / 4096MiB | 0% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 18262 G /usr/lib/Xorg 4MiB |
+-----------------------------------------------------------------------------------------+
```
i used envycontrol
`
doas envycontrol -s nvidia
`
but it gave me blackscreen when i started X11 server so i had to delete the `X11/xorg.conf` for it to work.
now iam using `envycontrol -s hybrid` trying to run ollama but its not detecting the GPU:
```
msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 45315"
Nov 14 18:58:27 Anondev ollama[88179]: time=2025-11-14T18:58:27.107+02:00 level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu
compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="19.2 GiB" available="3.4 GiB"
Nov 14 18:58:27 Anondev ollama[88179]: time=2025-11-14T18:58:27.107+02:00 level=INFO source=routes.go:1638 msg="entering low vram mode" "total vram"="0 B" threshold="20.0 GiB"
```
I don't know whats the problem from or how iam supposed to go about fixing it.
thanks for help!
Offline
Fixed by installing ollama-cuda
Offline
\o/
Please always remember to mark resolved threads by editing your initial posts subject - so others will know that there's no task left, but maybe a solution to find.
Thanks.
Offline