llm-vram-calculator
Free LLM VRAM calculator core behind modelvram.com: GPU memory for weights, KV cache and overhead of any Hugging Face model. MoE, MLA, sliding windows, GGUF; checked against public llama.cpp and vLLM logs.
159753a52/llm-vram-calculator
View on GitHub ↗Free LLM VRAM calculator core behind modelvram.com: GPU memory for weights, KV cache and overhead of any Hugging Face model. MoE, MLA, sliding windows, GGUF; checked against public llama.cpp and vLLM logs.
llm-vram-calculator ranks 300th of 301 in Inference Optimization, actively maintained, last commit 11 days ago.
Star trajectory
17 days tracked- in 30d, below the Inference Optimization median of +1.5%.
Last commit 11 days ago, fresher than the median of 14d.
How it compares in Inference Optimization
Ranked 300th of 301 by stars.
- Language
- TypeScript
- License
- MIT License
- Contributors
- 1
- Forks
- 0
- Watchers
- 0
- Open issues
- 0
- Releases
- 0
- Created
- 2026-09-26
- Stars this week
- +0
You've seen where llm-vram-calculator stands today.
Get the moves before everyone else: the 5 Inference Optimization repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.