hf_mem estimates the required memory for inference, including model weights and an optional KV cache, for Safetensors and GGUF for models on the Hugging Face Hub using HTTP Range requests i.e., without downloading or loading any weights locally.
When to use?
- User asks how much VRAM or memory a model needs to run
- User wants to know if a model fits on their GPU or a given instance
- User references a Hugging Face model ID or URL and asks about inference requirements
What are the requirements?
uvinstalled (foruvx)HF_TOKENenv var or--hf-tokenflag (for gated or private models only)
How to run?
Run with --model-id pointing to the Hugging Face Hub repository which will check that it either contains Safetensors (via model.safetensors, model.safetensors.index.json if sharded, or model_index.json for Diffusers) or GGUF model weights within.
If the repository contains GGUF model weights in multiple precisions / quantizations, the estimations will be on a per-file basis, whereas for inference you won't load all of those but rather only a single precision. This being said, for GGUF you might as well need to provide --gguf-file to target the specific file (or path if sharded) you want to run.
Additionally, hf-mem comes with an --experimental flag that will also calculate the KV cache memory requirements too, useful for large-language models, meaning it applies to LLMs (...ForCausalLM), VLMs (...ForConditionalGeneration), and GGUF models.
As per the context window, it will be read from the default or overridden with --max-model-len a la vLLM. And, same goes for the KV cache precision, which will default to the model precision unless manually set via --kv-cache-dtype a la vLLM too.
For Safetensors use as:
And, for GGUF use as:
Examples
For Transformers with Safetensors weights:
For Diffusers with Safetensors weights:
For Sentence Transformers with Safetensors weights:
With --experimental to include the KV cache estimation for LLMs and VLMs:
And, for LLMs or VLMs with GGUF weights:
