Verified working procedure • RTX 5060 Ti • Ollama VM

Proxmox GPU passthrough for an Ollama local LLM server.

Operational checklist and command guide for binding an NVIDIA GeForce RTX 5060 Ti to vfio-pci, passing it into an Ubuntu Ollama VM, and exposing Ollama to a Hermes/Godzilla VM over LAN/API.

Execution Progress0 of 0 complete
16Sections
RTX5060 Ti
VFIOTarget driver

Step 1

Confirm GPU exists

Verify Proxmox sees the RTX 5060 Ti GPU and audio function.

Verified
Confirm GPU visibility
lspci | grep -i -E "nvidia|vga|3d"
Verified result
01:00.0 VGA compatible controller: NVIDIA Corporation GB206 [GeForce RTX 5060 Ti] (rev a1)
01:00.1 Audio device: NVIDIA Corporation GB206 High Definition Audio Controller (rev a1)

Step 2

Confirm IOMMU

Verify Intel VT-d / IOMMU is active before passthrough work.

Verified
Check IOMMU messages
dmesg | grep -e DMAR -e IOMMU -e AMD-Vi
Verified result
DMAR: IOMMU enabled
DMAR: Intel(R) Virtualization Technology for Directed I/O

Step 3

Check driver state

Confirm current kernel driver and module state.

Action
Check current GPU drivers
lspci -nnk -s 01:00.0
lspci -nnk -s 01:00.1
lsmod | grep -E "vfio|nouveau|nvidia" || true
Desired driver
Kernel driver in use: vfio-pci

Step 4

Host driver rule

Do not install NVIDIA drivers on the Proxmox host.

Action
Do not install on Proxmox host
apt install nvidia-driver nvidia-smi

Step 5

Load VFIO modules

Load vfio, vfio_iommu_type1, and vfio_pci at boot.

Action
Create VFIO modules file
cat > /etc/modules-load.d/vfio.conf <<'EOF'
vfio
vfio_iommu_type1
vfio_pci
EOF
Verify VFIO modules file
cat /etc/modules-load.d/vfio.conf

Step 6

Bind GPU to VFIO

Bind PCI IDs 10de:2d04 and 10de:22eb to vfio-pci.

Action
Create VFIO binding config
cat > /etc/modprobe.d/vfio.conf <<'EOF'
options vfio-pci ids=10de:2d04,10de:22eb disable_vga=1
EOF
Verify VFIO binding
cat /etc/modprobe.d/vfio.conf

Step 7

Blacklist host GPU drivers

Prevent nouveau/nvidia from grabbing the GPU.

Action
Create GPU blacklist
cat > /etc/modprobe.d/blacklist-gpu.conf <<'EOF'
blacklist nouveau
blacklist nvidia
blacklist nvidiafb
blacklist nvidia_drm
blacklist nvidia_modeset
blacklist nvidia_uvm
options nouveau modeset=0
EOF
Verify blacklist
cat /etc/modprobe.d/blacklist-gpu.conf

Step 8

Rebuild and reboot

Rebuild initramfs and reboot into VFIO state.

Action
Rebuild initramfs and reboot
update-initramfs -u -k all
reboot

Step 9

Verify passthrough readiness

Confirm both GPU functions use vfio-pci.

Verified
Post-reboot verification
echo "=== GPU ==="
lspci -nnk -s 01:00.0

echo "=== GPU AUDIO ==="
lspci -nnk -s 01:00.1

echo "=== MODULES ==="
lsmod | grep -E "vfio|nouveau|nvidia" || true
Success criteria
01:00.0 GPU        Kernel driver in use: vfio-pci
01:00.1 GPU Audio  Kernel driver in use: vfio-pci
nouveau is not loaded
vfio modules are loaded

Step 10

Create Ollama VM

Use q35, OVMF/UEFI, CPU host, VirtIO, 32GB+ RAM.

Action
Recommended VM settings
OS: Ubuntu Server 24.04 LTS
Machine: q35
BIOS: OVMF / UEFI
CPU Type: host
Disk Controller: VirtIO SCSI
Network: VirtIO
RAM: 32GB+ recommended
CPU Cores: 8+ recommended

Step 11

Add PCI device

Add RTX 5060 Ti with All Functions, PCI-Express, ROM-Bar, Primary GPU.

Action
Proxmox GUI path
Ollama VM → Hardware → Add → PCI Device
Required options
All Functions: checked
PCI-Express: checked
ROM-Bar: checked
Primary GPU: checked

Step 12

Install NVIDIA in VM

Install NVIDIA driver inside the Ollama VM only.

Action
Install NVIDIA driver inside VM
sudo apt update
sudo apt install -y ubuntu-drivers-common
ubuntu-drivers devices
sudo ubuntu-drivers autoinstall
sudo reboot
Verify NVIDIA inside VM
nvidia-smi

Step 13

Install Ollama

Install Ollama, run a model, verify GPU usage.

Action
Install Ollama
curl -fsSL https://ollama.com/install.sh | sh
Verify and run test model
ollama --version
ollama run llama3.2:3b
nvidia-smi

Step 14

Expose Ollama API

Bind Ollama to 0.0.0.0:11434 and test from Hermes VM.

Action
Edit Ollama service override
sudo systemctl edit ollama
Service override content
[Service]
Environment="OLLAMA_HOST=0.0.0.0:11434"
Reload and test
sudo systemctl daemon-reload
sudo systemctl restart ollama
ss -tulpn | grep 11434
curl http://OLLAMA_VM_IP:11434/api/tags

Step 15

Troubleshooting

Fix nouveau binding, IOMMU, display loss, and host driver mistakes.

Action
If GPU is still using nouveau
cat /etc/modprobe.d/blacklist-gpu.conf
cat /etc/modprobe.d/vfio.conf
cat /etc/modules-load.d/vfio.conf
update-initramfs -u -k all
reboot
IOMMU boot parameters
intel_iommu=on iommu=pt
amd_iommu=on iommu=pt

Step 16

Final verified state

Confirm vfio-pci, IOMMU enabled, nouveau unloaded, vfio modules loaded.

Verified
Final verified state
01:00.0 RTX 5060 Ti GPU       Kernel driver in use: vfio-pci
01:00.1 RTX 5060 Ti Audio     Kernel driver in use: vfio-pci
IOMMU                         enabled
nouveau                       not loaded
vfio modules                  loaded
Verified hardware/kernel
NVIDIA GeForce RTX 5060 Ti
GPU PCI ID:   10de:2d04
Audio PCI ID: 10de:22eb
Proxmox kernel: 6.17.2-1-pve

Operational warning

Host display and driver boundary

After the GPU is bound to VFIO, Proxmox may lose local monitor output if the RTX 5060 Ti was the only display adapter. Manage Proxmox through Web UI or SSH. Install NVIDIA drivers inside the Ollama VM only.

Important