Blue-No1 / model-storage-strategy Public

Notifications You must be signed in to change notification settings
Fork 0
Star 0

Notes & comparisons on storage options for large LLMs (Work-in-progress)

0 stars 0 forks Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 5 Commits
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md
notes.md		notes.md
storage-costs.md		storage-costs.md

Repository files navigation

Model Storage Strategy

Notes & comparisons on where to store large open-weight LLMs.
Ghi chú & so sánh các phương án lưu trữ mô hình open-weight dung lượng lớn.

⚠️ Work in progress / Đang trong quá trình nghiên cứu

Options

Local NVMe: fastest but limited capacity, no scalability.
Google Cloud Storage (GCS): good for Vertex AI integration, per-GB cost.
Amazon S3: widely supported, ecosystem mature.
Hugging Face Hub: free hosting for smaller repos, community-friendly.

Progress Log

[YYYY-MM-DD] Init repo.
[YYYY-MM-DD] Added cost comparison notes.

Notes on Model Storage Strategy

About

Notes & comparisons on storage options for large LLMs (Work-in-progress)

cloud-storage research-notes mlops llm open-weight

Report repository

Releases

No releases published

Packages

No packages published