# clipseg-rd64-refined by CAMPUS INSTITUTE DATA SCIENCE (CIDAS) Source: https://savrn.com/models/clipseg-rd64-refined Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve clipseg-rd64-refined (151M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 0.3 GB | 0.4 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.2 GB | 0.2 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.1 GB | 0.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 22, 2026. [clipseg-rd64-refined on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/clipseg-rd64-refined/gpus) ## SAVRN's Notes on clipseg-rd64-refined Give it a picture and a phrase, or a picture and a reference image, and it returns a segmentation mask. CIDAS built clipseg-rd64-refined for zero-shot and one-shot image segmentation from text and image prompts, per Lüddecke et al., arXiv:2112.10003. The text side takes at most 77 tokens, so prompts are short labels, not descriptions. The 151M parameters are stored in float32, which is why the download is 1.2 GB while the 16-bit run needs only 0.4 GB. The cheapest Index setup is one MI300X with 192 GB at $1.85 per hour. Apache 2.0 covers commercial use, modification and redistribution, with notices kept. The rd64 in the name is a reduce dimension of 64, and refined means the variant with the more complex convolution, so match the checkpoint to what your pipeline was tuned against. Released November 1, 2022, last updated December 11, 2024, so confirm the revision. SAVRN Research, 2026-09-18 ## Model Card By CAMPUS INSTITUTE DATA SCIENCE (CIDAS), published under apache-2.0, revision 999e0328d9e1. CLIPSeg model with reduce dimension 64, refined (using a more complex convolution). It was introduced in the paper Image Segmentation Using Text and Image Prompts by Lüddecke et al. and first released in this repository. This model is intended for zero-shot and one-shot image segmentation. Refer to the documentation. Read CAMPUS INSTITUTE DATA SCIENCE (CIDAS)'s full model card ### CLIPSeg model CLIPSeg model with reduce dimension 64, refined (using a more complex convolution). It was introduced in the paper [Image Segmentation Using Text and Image Prompts](https://savrn.com/papers/image-segmentation-using-text-and-image-prompts) by Lüddecke et al. and first released in [this repository](https://github.com/timojl/clipseg). ### Intended use cases This model is intended for zero-shot and one-shot image segmentation. ### Usage Refer to the [documentation](https://huggingface.co/docs/transformers/main/en/model_doc/clipseg). ## Configuration Architecture CLIPSegForImageSegmentation Context length (tokens) 77 Layers 12 Hidden size 512 Feed-forward size 2,048 Attention heads 8 Vocabulary size 49,408 Stored precision float32 Model type clipseg ## Identity and Version Repository CIDAS/clipseg-rd64-refined Publisher CAMPUS INSTITUTE DATA SCIENCE (CIDAS) Task Image segmentation Modality Image Library transformers Parameters 151M parameters Languages Not stated by the source Revision 999e0328d9e10b484360c477313983f9afdd7050 First published 2022-11-01 Last updated 2024-12-11 ## Files and Weights 10 files, 1.2 GB in total. The weights are 2 files totalling 1.2 GB in bin, safetensors. Weights2 files · 1.2 GB Configuration3 files · 5.6 KB Tokenizer3 files · 1.6 MB Documentation1 file · 596 B Repository1 file · 1.4 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 603.0 MB | d00ca85d6b85 | | pytorch_model.bin | Weights | 603.1 MB | dd9308225b83 | | config.json | Configuration | 4.7 KB | — | | preprocessor_config.json | Configuration | 380 B | — | | special_tokens_map.json | Configuration | 472 B | — | | README.md | Documentation | 596 B | — | | .gitattributes | Repository | 1.4 KB | — | | merges.txt | Tokenizer | 524.6 KB | — | | tokenizer_config.json | Tokenizer | 974 B | — | | vocab.json | Tokenizer | 1.1 MB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 1.2 GB [Download from CAMPUS INSTITUTE DATA SCIENCE (CIDAS)](https://huggingface.co/CIDAS/clipseg-rd64-refined) Released by CAMPUS INSTITUTE DATA SCIENCE (CIDAS) through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Described by [arXiv:2112.10003](https://savrn.com/papers/image-segmentation-using-text-and-image-prompts) ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 1.2 GB | | 16-bit | 0.3 GB | | 8-bit | 0.2 GB | | 4-bit | 0.1 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About clipseg-rd64-refined ### How much GPU memory does clipseg-rd64-refined need? About 0.4 GB at 16-bit and 0.1 GB at 4-bit: the weights (151M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run clipseg-rd64-refined on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### Can I use clipseg-rd64-refined commercially? Yes. clipseg-rd64-refined is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors. ### What is clipseg-rd64-refined's context length? 77 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Image segmentation ### [clipseg-rd64](https://savrn.com/models/clipseg-rd64) [CAMPUS INSTITUTE DATA SCIENCE (CIDAS)](https://savrn.com/model-publishers/cidas) CLIPSeg model with reduce dimension 64. It was introduced in the paper Image Segmentation Using Text and Image Prompts by Lüddecke et al. and first released in this repository. This model is intended for zero-shot and one-shot image segmentation. Refer to the documentation. Open weights apache-2.0 151M parameters 77 tokens transformers [View model](https://savrn.com/models/clipseg-rd64) Model · Image segmentation ### [mask2former-swin-base-ade-semantic](https://savrn.com/models/mask2former-swin-base-ade-semantic) [AI at Meta](https://savrn.com/model-publishers/facebook) Mask2Former model trained on ADE20k semantic segmentation (base-sized version, Swin backbone). It was introduced in the paper Masked-attention Mask Transformer for Universal Image Segmentation and first released in this repository. Disclaimer: The team releasing Mask2Former did not write a model card for this model so this model card has been written by the Hugging Face team. Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding labels. Hence, all 3 tasks are treated as if they were instance segmentation. Mask2Former outperforms the previous SOTA, MaskFormer both in terms of performance an efficiency by (i)… Open weights other 107M parameters transformers [View model](https://savrn.com/models/mask2former-swin-base-ade-semantic) Model · Image segmentation ### [mask2former-swin-base-coco-panoptic](https://savrn.com/models/mask2former-swin-base-coco-panoptic) [AI at Meta](https://savrn.com/model-publishers/facebook) Mask2Former model trained on COCO panoptic segmentation (base-sized version, Swin backbone). It was introduced in the paper Masked-attention Mask Transformer for Universal Image Segmentation and first released in this repository. Disclaimer: The team releasing Mask2Former did not write a model card for this model so this model card has been written by the Hugging Face team. Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding labels. Hence, all 3 tasks are treated as if they were instance segmentation. Mask2Former outperforms the previous SOTA, MaskFormer both in terms of performance an efficiency by (i)… Open weights other 107M parameters transformers [View model](https://savrn.com/models/mask2former-swin-base-coco-panoptic) Model · Image segmentation ### [BEN2](https://savrn.com/models/ben2) [BackgroundErase](https://savrn.com/model-publishers/pramallc) BEN2 (Background Erase Network) introduces a novel approach to foreground segmentation through its innovative Confidence Guided Matting (CGM) pipeline. The architecture employs a refiner network that targets and processes pixels where the base model exhibits lower confidence levels, resulting in more precise and reliable matting results. This model is built on BEN: BEN2 was trained on the DIS5k and our 22K proprietary segmentation dataset. Our enhanced model delivers superior performance in hair matting, 4K processing, object segmentation, and edge refinement. Our Base model is open source. To try the full model through our free web demo or integrate BEN2 into your project with our API… Open weights mit 95M parameters ben2 [View model](https://savrn.com/models/ben2) Model · Image segmentation ### [dinov3-pointing-pilot-v1](https://savrn.com/models/dinov3-pointing-pilot-v1) [Fire Viewer](https://savrn.com/model-publishers/fireviewer) Research archive, currently publicly visible on the Hub, of a five-epoch DINOv3 ViT-B/16 multi-task pilot for visible fire/smoke presence, segmentation, point localization and explicit visual abstention. This repository preserves a completed, reloadable experiment. It is not a production model and not independently benchmarked. The retained release records describe a private pilot policy; current public visibility does not resolve that restriction or establish redistribution permission. The word “pilot” is part of the model identity and should not be removed in downstream documentation. The metrics below come from the campaign validation split. They are not an independent benchmark and must… Open weights other 94M parameters pytorch [View model](https://savrn.com/models/dinov3-pointing-pilot-v1) Model · Image segmentation ### [MicroStructFormer](https://savrn.com/models/microstructformer) [Nianqi Deng](https://savrn.com/model-publishers/dnq2025) MicroStructFormer is a high-capacity Mask2Former model built on a Swin-Large backbone, designed for the semantic segmentation of ultrastructures in Electron Microscopy (EM) images. This model has been trained to accurately segment the following critical ultrastructural elements: Note: While the model architecture theoretically supports axon and myelin segmentation, this specific release is optimized and calibrated for the classes listed below due to dataset annotations. You can use this model easily via the transformers library. This Hugging Face model repository is associated with the following bioRxiv preprint: These model weights and associated architectures are provided for… Open weights cc-by-nc-sa-4.0 216M parameters transformers [View model](https://savrn.com/models/microstructformer) ## CAMPUS INSTITUTE DATA SCIENCE (CIDAS) [All models and datasets](https://savrn.com/model-publishers/cidas) ## Versions - [999e0328d9e1](https://savrn.com/models/clipseg-rd64-refined/versions/999e0328d9e1) · current 2026-09-22 ## Explore More - [All image segmentation models](https://savrn.com/models/tasks/image-segmentation) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-19. - [Hugging Face record](https://huggingface.co/CIDAS/clipseg-rd64-refined) - [How the hub is built](https://savrn.com/model-hub/methodology)