depthark

depthark/wattllama

How many watts does your local LLM really burn? Live power, temperature and energy-per-token dashboard for Windows: llama.cpp, Ollama, LM Studio. No admin, no drivers, 0 dependencies.

5 good first / help-wanted issues · JavaScript · last activity Oct 18, 2026

3 stars 0 forks 3 watchers JavaScript MIT License
dashboard energy energy-monitoring gpu gpu-monitoring hardware-monitor inference llama-cpp llm lm-studio local-llm nvidia ollama power-monitoring self-hosted tokens windows
View on GitHub
5 Open Issues Need Help Last updated: Oct 18, 2026

Open Issues Need Help

View All on GitHub
Hardware: Linux on real machines, please confirm 17 days ago
help wanted hardware
depthark/wattllama
3

How many watts does your local LLM really burn? Live power, temperature and energy-per-token dashboard for Windows: llama.cpp, Ollama, LM Studio. No admin, no drivers, 0 dependencies.

JavaScript
#dashboard#energy#energy-monitoring#gpu#gpu-monitoring#hardware-monitor#inference#llama-cpp#llm#lm-studio#local-llm#nvidia#ollama#power-monitoring#self-hosted#tokens#windows
Hardware: CPU power on AMD Ryzen (Energy Meter counters?) 17 days ago
help wanted good first issue hardware
depthark/wattllama
3

How many watts does your local LLM really burn? Live power, temperature and energy-per-token dashboard for Windows: llama.cpp, Ollama, LM Studio. No admin, no drivers, 0 dependencies.

JavaScript
#dashboard#energy#energy-monitoring#gpu#gpu-monitoring#hardware-monitor#inference#llama-cpp#llm#lm-studio#local-llm#nvidia#ollama#power-monitoring#self-hosted#tokens#windows
Hardware: Intel Arc GPU power via LibreHardwareMonitor, please confirm 17 days ago
help wanted hardware
depthark/wattllama
3

How many watts does your local LLM really burn? Live power, temperature and energy-per-token dashboard for Windows: llama.cpp, Ollama, LM Studio. No admin, no drivers, 0 dependencies.

JavaScript
#dashboard#energy#energy-monitoring#gpu#gpu-monitoring#hardware-monitor#inference#llama-cpp#llm#lm-studio#local-llm#nvidia#ollama#power-monitoring#self-hosted#tokens#windows
Hardware: AMD Radeon GPU power via LibreHardwareMonitor, please confirm 17 days ago
help wanted hardware
depthark/wattllama
3

How many watts does your local LLM really burn? Live power, temperature and energy-per-token dashboard for Windows: llama.cpp, Ollama, LM Studio. No admin, no drivers, 0 dependencies.

JavaScript
#dashboard#energy#energy-monitoring#gpu#gpu-monitoring#hardware-monitor#inference#llama-cpp#llm#lm-studio#local-llm#nvidia#ollama#power-monitoring#self-hosted#tokens#windows
Engine: KoboldCpp adapter 17 days ago
help wanted good first issue engine
depthark/wattllama
3

How many watts does your local LLM really burn? Live power, temperature and energy-per-token dashboard for Windows: llama.cpp, Ollama, LM Studio. No admin, no drivers, 0 dependencies.

JavaScript
#dashboard#energy#energy-monitoring#gpu#gpu-monitoring#hardware-monitor#inference#llama-cpp#llm#lm-studio#local-llm#nvidia#ollama#power-monitoring#self-hosted#tokens#windows