SAVRN Model Hub · Comparisons
CLIP-ViT-B-32-laion2B-s34B-b79K vs fashion-clip
CLIP-ViT-B-32-laion2B-s34B-b79K has 151M parameters and fashion-clip has 151M parameters; both are released under MIT License; at 16-bit, CLIP-ViT-B-32-laion2B-s34B-b79K needs about 0.4 GB (1x MI300X from $1.85 an hour) and fashion-clip about 0.4 GB (1x MI300X from $1.85 an hour).
| Field | CLIP-ViT-B-32-laion2B-s34B-b79K laion/CLIP-ViT-B-32-laion2B-s34B-b79K | fashion-clip patrickjohncyh/fashion-clip |
|---|---|---|
| Publisher | LAION eV | Patrick John Chia |
| Task | Zero shot image classification | Zero shot image classification |
| Modality | Other | Other |
| Parameters, as reported | 151M parameters | 151M parameters |
| Architecture | CLIPModel | CLIPModel |
| Library | open_clip | transformers |
| Context length | 77 tokens | 77 tokens |
| Repository size | 2.4 GB | 1.8 GB |
| Artifact formats | safetensors, pytorch | safetensors, onnx, pytorch |
| License | mit | mit |
| Access | Open weights, no gate | Open weights, no gate |
| Memory at 16-bit (weights and margin) | 0.4 GB | 0.4 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 0.1 GB | 0.1 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | 1a25a446712b | 7e3ba62ce16b |
| Downloads reported by the hub | 3.8M | 2.2M |
| Last observed | 2026-09-18 | 2026-09-18 |
An evaluation row appears only where at least two of these models report the same benchmark with the same stated configuration, metric, unit and setup. Different evaluators stay named in each cell. Values are shown as reported: no unit conversion, no ranking.
SAVRN's Notes on CLIP-ViT-B-32-laion2B-s34B-b79K
On disk it is 2.4 GB across 14 files, stored in float32; in 16-bit it needs 0.4 GB, and 8-bit halves that to 0.2 GB. The cheapest setup we list, one MI300X with 192 GB at $1.85 an hour, dwarfs a 151M-parameter zero-shot image classifier, so share the card. The text side reads 77 tokens, which keeps the labels you pair with images short, and the training data was the LAION-2B English subset of LAION-5B.
MIT is a short license: commercial use, modification and redistribution are allowed as long as the copyright and permission notices ride along. Set that against the publisher's framing, which calls the model a research output for research communities; the license allows a production deployment, the stated intent does not describe one. Check the serving stack too: the library is open_clip, not transformers, and the one paper on file is arXiv:1910.04867.
Questions
Which is larger, CLIP-ViT-B-32-laion2B-s34B-b79K or fashion-clip?
CLIP-ViT-B-32-laion2B-s34B-b79K (151M parameters) is larger than fashion-clip (151M parameters), by the parameter counts their publishers report.
Which is cheaper to run, CLIP-ViT-B-32-laion2B-s34B-b79K or fashion-clip?
At 4-bit, CLIP-ViT-B-32-laion2B-s34B-b79K fits on 1x MI300X from $1.85 an hour and fashion-clip on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use CLIP-ViT-B-32-laion2B-s34B-b79K commercially?
Yes. CLIP-ViT-B-32-laion2B-s34B-b79K is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.
Can I use fashion-clip commercially?
Yes. fashion-clip is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.