LLM VRAM Calculator
VRAM for LLMs by context, users, vLLM or llama.cpp
Runs in the browser on Hugging Face
- 2
- mit
- 6 wk ago
VRAM for LLMs by context, users, vLLM or llama.cpp
Runs in the browser on Hugging Face
How much GPU memory a model needs, and which GPUs fit it
Runs in the browser on Hugging Face
VRAM any HF model needs + live GPU rental prices
Runs in the browser on Hugging Face
VRAM and RAM per quant, from the 48 shard headers
Runs in the browser on Hugging Face
VRAM and RAM per quant: Qwen3.8, DeepSeek V4.1, Gemma 4
Runs in the browser on Hugging Face
VRAM any HF model needs + live GPU rental prices
Runs in the browser on Hugging Face