Ollama GPU usage validation
From Notes_Wiki
Revision as of 12:36, 2 February 2025 by Saurabh (talk | contribs) (Created page with "Home > Local system based AI tools > Ollama > Ollama GPU usage validation =Ollama GPU usage validation= # Verify `/etc/systemd/system/ollama.service` has below line: #:<pre> #:: Environment="OLLAMA_FLASH_ATTENTION=1" #:</pre> # Run below in one terminal to monitor GPU usage including processes using GPU #:<pre> #:: watch nvidia-smi #:</pre> # Run some model on second terminal such as: #:<pre> #:: ollama run deepseek-r1:8b #:</pre> # In nvidia-s...")
Home > Local system based AI tools > Ollama > Ollama GPU usage validation
Ollama GPU usage validation
- Verify `/etc/systemd/system/ollama.service` has below line:
- Environment="OLLAMA_FLASH_ATTENTION=1"
- Run below in one terminal to monitor GPU usage including processes using GPU
- watch nvidia-smi
- Run some model on second terminal such as:
- ollama run deepseek-r1:8b
- In nvidia-settings graphical output, click on GPU 0 - <GPU name> and see information about 'GPU Utilization:'
- In third terminal if you use “ollama ps” we can see how much of CPU is being used and how much GPU
ollama ps NAME ID SIZE PROCESSOR UNTIL deepseek-r1:8b 28f8fd6cdc67 6.3 GB 35%/65% CPU/GPU 4 minutes from now
Home > Local system based AI tools > Ollama > Ollama GPU usage validation
