# Increasing model download speeds from Hugging Face
**URL:** https://forum.verda.com/t/increasing-model-download-speeds-from-hugging-face/40
**Category:** Product Q&A
**Created:** [September 3, 2025, 8:05am UTC](https://forum.verda.com/t/increasing-model-download-speeds-from-hugging-face/40 "2025-09-03T08:05:28Z")
**Posts on this page:** 2
**Page:** 1
### Author:  [@Alpaca](https://forum.verda.com/u/Alpaca)
#### Post date: [September 3, 2025, 8:05am UTC](https://forum.verda.com/t/increasing-model-download-speeds-from-hugging-face/40/1 "2025-09-03T08:05:28Z")
Hi, What optimizations would you recommend for increasing model download speeds from Hugging Face?
---
### Author:  [@TeamVerda](https://forum.verda.com/u/TeamVerda)
#### Post date: [September 3, 2025, 10:16am UTC](https://forum.verda.com/t/increasing-model-download-speeds-from-hugging-face/40/2 "2025-09-03T10:16:19Z")
Hi,
There are multiple optimizations depending on the model, some of the quick and easy changes:
- set `HF_HOME` to your SFS (Shared Filesystem) or NVMe drive (read about Cache management: [https://huggingface.co/docs/datasets/en/cache](https://huggingface.co/docs/datasets/en/cache))
- use `HF_HUB_ENABLE_HF_TRANSFER=1`
Use `hf_transfer`, more on their docs site: [https://huggingface.co/docs/hub/en/models-downloading](https://huggingface.co/docs/hub/en/models-downloading)
HF transfer helps usually if you have 100s of 4-9 gb files. Sometimes in HF there are these huge 45 gb files (example Qwen Image, Wan 2.2) They make the downloads quite slow.
Most good llm models have shards of size 9gb so can make excellent use of HF\_TRANSFER
For [reference](https://github.com/huggingface/huggingface_hub/blob/b698915d6b582c72806ac3e91c43bfd8dde35856/docs/source/en/guides/download.md?plain=1#L167C1-L191C218)