Skip to content
Local AI Wizard
Your machine
Theme

CLIP-ViT-H-14-laion2B-s32B-b79K

LAION · laion/CLIP-ViT-H-14-laion2B-s32B-b79K

Weights license: MIT · code and components may use other terms

Hub downloads · 30 days476KPopularity, not quality · read 2026-10-25
Memory needed~5 GB16-bit estimate · not measured
Parameters1 BHub safetensors total
Repository updated2025-01-22A commit is not a release date

Quality

No comparable score

We track no public, comparable benchmark that covers this model yet. No score is inferred.

Reported by the publisher

The publisher's card states no benchmark result for this checkpoint (read 2026-10-25). not published on the card · read 2026-10-25

Runs on

Fast memory holds it 118

The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.

Show all 118

One memory tier short 1

The same machines with the next memory size up would hold it in fast memory.

Hardware profiles grouped by a labelled 16-bit planning estimate from the Hugging Face parameter count (2 bytes per parameter, 20% allowance, 2 GB reserve): classic vision encoders are not usually quantized. Image size and batch change the real requirement. Not a measured fit.

Consider it for

LAION released CLIP-ViT-H-14-laion2B-s32B-b79K on 2022-09-15: an image-text encoder for zero-shot classification and retrieval, with 986M parameters on the Hugging Face count and the MIT license.

Check first

License: commercial use allowed. The 16-bit estimate is about 5 GB with reserve; image size and batch change the real figure.

Measured speed

No published measurement for this checkpoint

Tokens per second are shown only when a source publishes them with hardware, build and setup. They are never estimated.

How to run

Runtime compatibility and tokens per second have not been measured for this entry. Published metadata and a memory estimate do not prove a successful local run.

Library in source: open_clip

Documented ways to run it

The model card documents no command or code to run it

Choose my computer

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Task
zero-shot-image-classification
Architecture
CLIPModel
Library in source
open_clip
Weight license
MITlaion/CLIP-ViT-H-14-laion2B-s32B-b79K model card (Hugging Face) · read 2026-10-18source
Commercial use
Allowed MIT license text (SPDX) · read 2026-10-18license text
Released
Large scale openCLIP: L/14, H/14 and g/14 trained on LAION-2B - LAION blog (source in LAION-AI/laion.ai) · read 2026-10-18source
Every stored field12 fields
Revision checked
1c2b8495b28150b8a4922ee1c8edee224c284c0c
Architecture
CLIPModel
Library
open_clip
Hub task tag
zero-shot-image-classification
Formats
pytorch, safetensors
Access
Open download
Publisher kind
Official
Hub parameter count
986,109,774safetensors.total
Repository created
2022-09-14creation is not the model's release
Repository updated
2025-01-22a commit is not a release date
Hub downloads (30 days) · likes
475,977 · 486this repository only · read 2026-10-25
Catalog state
Hub config or weights found; no inventory benchmark link

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Curated facts checked: 2026-10-18. The license and release date cite the publisher's sources; parameters, files and task come from the Hugging Face record, and memory is a labelled estimate from its parameter count. A value no source states stays empty; a repository commit is not a model release date.