# Fix Ollama Not Using Your GPU

> Ollama ran on CPU instead of your GPU. Confirm it with ollama ps, then fix the driver, Docker and WSL passthrough, or a model too big for VRAM.

- Canonical: https://guides-ai.com/guides/ollama-gpu-not-detected/
- Plate 09.13 · Topic: Local LLMs (https://guides-ai.com/topics/local-llm/)
- Published: 19 Oct 2026 · 3 min read
- Source site: guides-ai — https://guides-ai.com/

Ollama offloads to the GPU automatically when it can. When it runs on CPU instead, generation crawls. The cause is usually a driver, a container, or a model too big for your VRAM, not a missing setting.

## 1. Check whether the GPU is actually used

```bash
ollama ps
```

Shows each loaded model and a PROCESSOR column: `100% GPU`, `100% CPU`, or a split like `48%/52% CPU/GPU`.

Watch utilisation live while a prompt runs:

```bash
nvidia-smi -l 1
```

A busy GPU during generation confirms offload; a flat 0% means it fell back to CPU. On Apple Silicon nothing needs configuring, since Metal is automatic, so skip to step 4.

## 2. Update the NVIDIA driver and CUDA runtime

Ollama needs compute capability 5.0+ and driver 550 or newer (570+ for cards from 5.0 to 6.2). Check what you have:

```bash
nvidia-smi
```

Prints the driver version and card; if it fails, the host has no working driver and Ollama cannot see a GPU. On Windows the GPU build is used once the driver is current; see [run Ollama on Windows](/guides/run-local-llm-ollama-windows/).

## 3. Fix GPU passthrough in Docker and WSL

In Docker the container needs the NVIDIA Container Toolkit, so confirm the runtime first:

```bash
docker run --gpus all ubuntu nvidia-smi
```

If that prints your GPU, run Ollama with `--gpus all`; if it errors, install the toolkit first. Under WSL2 the GPU comes from the Windows driver, so install that, not a driver inside the Linux distro.

## 4. Size the model to your VRAM

If a model is larger than free VRAM, Ollama keeps some layers on the GPU and the rest on CPU, the `48%/52%` split from step 1. Pick a smaller quantization or a smaller model for a full `100% GPU` load; see [how much RAM or VRAM a model needs](/guides/local-llm-ram-vram-requirements/) and [choose a quantization](/guides/choose-llm-quantization/).

## 5. Set the right GPU with device variables

```bash
CUDA_VISIBLE_DEVICES=GPU-<uuid> ollama serve
```

Pins Ollama to one card; list UUIDs with `nvidia-smi -L`. For AMD the equivalent is `ROCR_VISIBLE_DEVICES`, and an unsupported AMD card may need `HSA_OVERRIDE_GFX_VERSION`.

**If it fails:**

- `ollama ps` still shows `100% CPU` after a Linux suspend/resume: reload the driver with `sudo rmmod nvidia_uvm && sudo modprobe nvidia_uvm`.
- The container worked, then dropped to CPU: add `"exec-opts": ["native.cgroupdriver=cgroupfs"]` to `/etc/docker/daemon.json` and restart Docker.
- An AMD GPU is ignored on Linux: add the ollama user to the `render` group, or set `AMD_LOG_LEVEL=3` and read the discovery error. Full matrix in the [Ollama GPU docs](https://docs.ollama.com/gpu).

Next: [fix CUDA out of memory when running a model](/guides/fix-cuda-out-of-memory/).