# xclip-large-patch14 by Microsoft: Open-Weight Model Source: https://savrn.com/models/xclip-large-patch14 Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve xclip-large-patch14 (576M 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 | 1.2 GB | 1.4 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 | 0.6 GB | 0.7 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 | 0.3 GB | 0.3 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 24, 2026. [xclip-large-patch14 on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/xclip-large-patch14/gpus) ## Model Card By Microsoft, published under mit, revision a9dd1429a16c. ### X-CLIP (large-sized model) X-CLIP model (large-sized, patch resolution of 14) trained fully-supervised on [Kinetics-400](https://www.deepmind.com/open-source/kinetics). It was introduced in the paper [Expanding Language-Image Pretrained Models for General Video Recognition](https://savrn.com/papers/expanding-language-image-pretrained-models-for-general-video-recognition) by Ni et al. and first released in [this repository](https://github.com/microsoft/VideoX/tree/master/X-CLIP). This model was trained using 8 frames per video, at a resolution of 224x224. Disclaimer: The team releasing X-CLIP did not write a model card for this model so this model card has been written by the Hugging Face team. ### Model description X-CLIP is a minimal extension of [CLIP](https://huggingface.co/docs/transformers/model_doc/clip) for general video-language understanding. The model is trained in a contrastive way on (video, text) pairs. This allows the model to be used for tasks like zero-shot, few-shot or fully supervised video classification and video-text retrieval. ### Intended uses & limitations You can use the raw model for determining how well text goes with a given video. See the [model hub](https://huggingface.co/models?search=microsoft/xclip) to look for fine-tuned versions on a task that interests you. [Read the full model card (259 words)](https://savrn.com/models/xclip-large-patch14/card) ## Configuration Architecture XCLIPModel Context length (tokens) 77 Layers 12 Hidden size 768 Feed-forward size 3,072 Attention heads 12 Vocabulary size 49,408 Stored precision float32 Model type xclip ## Identity and Version Repository microsoft/xclip-large-patch14 Publisher Microsoft Task Video classification Modality Video Library transformers Parameters 576M parameters Languages en Revision a9dd1429a16cf305df2aaea232d5e8dceba1c675 First published 2022-09-07 Last updated 2024-10-28 ## Files and Weights 11 files, 4.6 GB in total. The weights are 2 files totalling 4.6 GB in bin, safetensors. Weights2 files · 4.6 GB Configuration3 files · 9.7 KB Tokenizer4 files · 3.8 MB Documentation1 file · 2.7 KB Repository1 file · 1.4 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 2.3 GB | 5dfd16f191d7 | | pytorch_model.bin | Weights | 2.3 GB | 452ba339d9f0 | | config.json | Configuration | 8.9 KB | — | | preprocessor_config.json | Configuration | 310 B | — | | special_tokens_map.json | Configuration | 472 B | — | | README.md | Documentation | 2.7 KB | — | | .gitattributes | Repository | 1.4 KB | — | | merges.txt | Tokenizer | 524.6 KB | — | | tokenizer.json | Tokenizer | 2.2 MB | — | | tokenizer_config.json | Tokenizer | 927 B | — | | vocab.json | Tokenizer | 1.1 MB | — | ## License and Download License mit Access Open weights, no gate Download size 4.6 GB [Download from Microsoft](https://huggingface.co/microsoft/xclip-large-patch14) Released by Microsoft through its official repository on Hugging Face. [Read the license](https://opensource.org/license/mit). ## Built From - Described by [arXiv:2208.02816](https://savrn.com/papers/expanding-language-image-pretrained-models-for-general-video-recognition) ## Evaluations Each result is shown as reported, with the conditions its reporter stated. None is a SAVRN measurement. A comparison lines two results up only when their configuration, unit and setup are all stated and identical. | Benchmark | Conditions | Result | Reported by | Revision | Date | | --- | --- | --- | --- | --- | --- | | Kinetics 400 | Task video-classificationMetric top-1 accuracyComparison conditions not established | 87.1 | [microsoft](https://huggingface.co/microsoft/xclip-large-patch14) Publisher reported | Evaluated revision not stated | — | | Kinetics 400 | Task video-classificationMetric top-5 accuracyComparison conditions not established | 97.6 | [microsoft](https://huggingface.co/microsoft/xclip-large-patch14) Publisher reported | Evaluated revision not stated | — | ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 4.6 GB | | 16-bit | 1.2 GB | | 8-bit | 0.6 GB | | 4-bit | 0.3 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About xclip-large-patch14 ### How much GPU memory does xclip-large-patch14 need? About 1.4 GB at 16-bit and 0.3 GB at 4-bit: the weights (576M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run xclip-large-patch14 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 xclip-large-patch14 commercially? Yes. xclip-large-patch14 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. ### What is xclip-large-patch14's context length? 77 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Video classification ### [VideoMAEv2-Huge](https://savrn.com/models/videomaev2-huge) [OpenGVLab](https://savrn.com/model-publishers/opengvlab) VideoMAEv2-Huge model pre-trained for 1200 epochs in a self-supervised way on UnlabeldHybrid-1M dataset. It was introduced in the paper [[CVPR23]VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://arxiv.org/abs/2203.12602) by Wang et al. and first released in GitHub. You can use the raw model for video feature extraction. Here is how to use this model to extract a video feature Open weights cc-by-nc-4.0 632M parameters [View model](https://savrn.com/models/videomaev2-huge) Model · Video classification ### [vjepa2-vith-fpc64-256](https://savrn.com/models/vjepa2-vith-fpc64-256) [AI at Meta](https://savrn.com/model-publishers/facebook) A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of VJEPA, resulting in state-of-the-art video understanding capabilities, leveraging data and model sizes at scale. The code is released in this repository. To run V-JEPA 2 model, ensure you have installed the latest transformers: V-JEPA 2 is intended to represent any video (and image) to perform video classification, retrieval, or as a video encoder for VLMs. To load a video, sample the number of frames according to the model. For this model, we use 64. To load an image, simply copy the image to the desired number of frames. For more code examples, please refer to the V-JEPA 2… Open weights mit 654M parameters transformers [View model](https://savrn.com/models/vjepa2-vith-fpc64-256) Model · Video classification ### [vjepa2-vitl-fpc16-256-ssv2](https://savrn.com/models/vjepa2-vitl-fpc16-256-ssv2) [AI at Meta](https://savrn.com/model-publishers/facebook) A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of VJEPA, resulting in state-of-the-art video understanding capabilities, leveraging data and model sizes at scale. The code is released in this repository. This is V-JEPA 2 ViT-L 256 model with video classification head pretrained on Something-Something-V2 dataset. To run V-JEPA 2 model, ensure you have installed the latest transformers Open weights mit 375M parameters transformers [View model](https://savrn.com/models/vjepa2-vitl-fpc16-256-ssv2) Model · Video classification ### [vjepa2-vitl-fpc16-256-ssv2](https://savrn.com/models/vjepa2-vitl-fpc16-256-ssv2-2) [Pavel Iakubovskii](https://savrn.com/model-publishers/qubvel-hf) A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of VJEPA, resulting in state-of-the-art video understanding capabilities, leveraging data and model sizes at scale. The code is released in this repository. This is V-JEPA 2 model with video classification head pretrained on Something-Something-V2 dataset. To run V-JEPA 2 model, ensure you have installed the latest transformers Open weights mit 375M parameters transformers [View model](https://savrn.com/models/vjepa2-vitl-fpc16-256-ssv2-2) Model · Video classification ### [vjepa2-vitl-fpc32-256-diving48](https://savrn.com/models/vjepa2-vitl-fpc32-256-diving48) [AI at Meta](https://savrn.com/model-publishers/facebook) A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of VJEPA, resulting in state-of-the-art video understanding capabilities, leveraging data and model sizes at scale. The code is released in this repository. This is V-JEPA 2 ViT-L 256 model with video classification head pretrained on Diving 48 dataset. To run V-JEPA 2 model, ensure you have installed the latest transformers Open weights mit 375M parameters transformers [View model](https://savrn.com/models/vjepa2-vitl-fpc32-256-diving48) Model · Video classification ### [videomae-large](https://savrn.com/models/videomae-large) [Multimedia Computing Group-Nanjing University](https://savrn.com/model-publishers/mcg-nju) VideoMAE model pre-trained on Kinetics-400 for 1600 epochs in a self-supervised way. It was introduced in the paper VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training by Tong et al. and first released in this repository. Disclaimer: The team releasing VideoMAE did not write a model card for this model so this model card has been written by the Hugging Face team. VideoMAE is an extension of Masked Autoencoders (MAE) to video. The architecture of the model is very similar to that of a standard Vision Transformer (ViT), with a decoder on top for predicting pixel values for masked patches. Videos are presented to the model as a sequence of… Open weights cc-by-nc-4.0 343M parameters transformers [View model](https://savrn.com/models/videomae-large) ## Microsoft [All models and datasets](https://savrn.com/model-publishers/microsoft) ## Versions - [a9dd1429a16c](https://savrn.com/models/xclip-large-patch14/versions/a9dd1429a16c) · current 2026-09-18 ## Explore More - [All video classification models](https://savrn.com/models/tasks/video-classification) - [All models under mit](https://savrn.com/models/licenses/mit) - [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 2026-10-21. - [Microsoft website](https://github.com/microsoft) - [Hugging Face record](https://huggingface.co/microsoft/xclip-large-patch14) - [How the hub is built](https://savrn.com/model-hub/methodology)