Model reference · open weights
react-native-executorch-clip-vit-patch32 is an open-weight embedding model from software-mansion. Built for phones (ExecuTorch) — it does not run on a GPU server.
react-native-executorch-clip-vit-patch32 is a set of exported models for the React Native ExecuTorch library, designed for image feature extraction tasks. The package includes variants for CoreML, MLX, Vulkan, and XNNPACK backends with precision levels ranging from int8 to fp32. It is published under the MIT license and requires the ExecuTorch v1.4.1 runtime.
Summary of the software-mansion/react-native-executorch-clip-vit-base-patch32 model card, 2026-10-01
What it is
| Released by | software-mansion |
|---|---|
| Type | Embedding models |
| Task | Image embed |
| Runs with | executorch |
| Released | 2025-07-14 |
| Popularity | 9k downloads / month |
| Licence | Open weights |
From the model card
This repository hosts the clip-vit-base-patch32 models exported for the
React Native ExecuTorch
library as ExecuTorch .pte programs, ready to run on device.
Upstream model: clip-vit-base-patch32
| Path | Component | Backend | Precision |
|---|---|---|---|
coreml/clip_vit_base_patch32_image_coreml_fp16.pte | image | coreml | fp16 |
coreml/clip_vit_base_patch32_text_coreml_fp16.pte | text | coreml | fp16 |
mlx/clip_vit_base_patch32_image_mlx_int8.pte | - | mlx | int8 |
vulkan/clip_vit_base_patch32_image_vulkan_fp16.pte | image | vulkan | fp16 |
vulkan/clip_vit_base_patch32_text_vulkan_fp16.pte | text | vulkan | fp16 |
xnnpack/clip_vit_base_patch32_image_xnnpack_fp32.pte | image | xnnpack | fp32 |
xnnpack/clip_vit_base_patch32_text_xnnpack_fp32.pte | text | xnnpack | fp32 |
config.json 43 B
coreml/clip_vit_base_patch32_image_coreml_fp16.pte 168 MB
coreml/clip_vit_base_patch32_text_coreml_fp16.pte 122 MB
coreml/config.json 1.7 kB
mlx/clip_vit_base_patch32_image_mlx_int8.pte 93.7 MB
mlx/config.json 840 B
tokenizer.json 2.1 MB
vulkan/clip_vit_base_patch32_image_vulkan_fp16.pte 168 MB
vulkan/clip_vit_base_patch32_text_vulkan_fp16.pte 121 MB
vulkan/config.json 1.7 kB
xnnpack/clip_vit_base_patch32_image_xnnpack_fp32.pte 335 MB
xnnpack/clip_vit_base_patch32_text_xnnpack_fp32.pte 242 MB
xnnpack/config.json 1.6 kB
These files are published for the ExecuTorch v1.4.1 runtime. ExecuTorch gives no forward compatibility guarantee, so an older runtime may fail to load them.
To use them in React Native ExecuTorch, pass the model constant shipped in the library's model registry to the corresponding task pipeline. See the documentation.
To load these files in your own ExecuTorch runtime, read the compatibility note first.
Quoted from the model card on Hugging Face — the full card is behind the Hugging Face link above.
How it works
Running it
Built for phones (ExecuTorch) — it does not run on a GPU server.