vramwatch

The flame graph for "why won't this model fit": live-trace local-LLM VRAM (weights vs KV cache) and predict max context before OOM. Zero-dependency Go, AMD/ROCm first-class, Ollama & llama.cpp.

amd

View on GitHub

1 Stars

0 Forks

0 Watchers

Go Language

apache-2.0 License

37 SrcLog Score

Cost to Build

$24.2K

Market Value

$10.8K

How is this calculated?

Growth over time

2 data points · 2026-07-26 → 2026-08-09

Stars Forks Watchers

💬

How do you feel about this project?

Ask AI about vramwatch

Question copied to clipboard

What is the RamazanKara/vramwatch GitHub project? Description: "The flame graph for "why won't this model fit": live-trace local-LLM VRAM (weights vs KV cache) and predict max context before OOM. Zero-dependency Go, AMD/ROCm first-class, Ollama & llama.cpp.". Written in Go. Explain what it does, its main use cases, key features, and who would benefit from using it.

Question is copied to clipboard — paste it after the AI opens.

How to clone vramwatch

Clone via HTTPS

git clone https://github.com/RamazanKara/vramwatch.git

Clone via SSH

[email protected]:RamazanKara/vramwatch.git

Download ZIP

Download main.zip

Found an issue?

Report bugs or request features on the vramwatch issue tracker:

Open GitHub Issues

Similar to vramwatch

webpack madge steal wufuc conditioner awesome-vulkan esl zydis staxrip pyopencl coriander lodjs easytimer.js ocl angular-async-loader node-dependency-tree purge-wrangler require-vuejs GatelessGateSharp SimpleSvm set-egpu parenchyma node-precinct TypeScript-AMD-Boilerplate ScanTree awesome-d3d12 Tensile generator-module-boilerplate akase romania-choropleth