Model reference · open weights

react-native-executorch-multi-qa-MiniLM-L6-cos

Not for GPU servers Embeddings software-mansion Embeddings 1 build Open weights 1k dl/mo

react-native-executorch-multi-qa-MiniLM-L6-cos is an open-weight embedding model from software-mansion. Built for phones (ExecuTorch). It does not run on a GPU server.

  • The react-native-executorch-multi-qa-MiniLM-L6-cos model is a sentence-similarity model exported for the React Native ExecuTorch library.
  • It is available in coreml, vulkan, and xnnpack variants with fp16 or fp32 precision, and is compatible with the ExecuTorch v1.4.1 runtime.
  • The model is published under the apache-2.0 licence.

Summary of the software-mansion/react-native-executorch-multi-qa-MiniLM-L6-cos-v1 model card, 2026-10-01

What it is

Released bysoftware-mansion
Released2025-05-07

From the model card

What software-mansion says about react-native-executorch-multi-qa-MiniLM-L6-cos

Read the model card

This repository hosts the multi-qa-MiniLM-L6-cos-v1 models exported for the React Native ExecuTorch library as ExecuTorch .pte programs, ready to run on device.

Upstream model: multi-qa-MiniLM-L6-cos-v1

Variants

PathBackendPrecision
coreml/multi_qa_minilm_l6_cos_v1_coreml_fp16.ptecoremlfp16
vulkan/multi_qa_minilm_l6_cos_v1_vulkan_fp16.ptevulkanfp16
xnnpack/multi_qa_minilm_l6_cos_v1_xnnpack_fp32.ptexnnpackfp32

Repository structure

config.json                                         47 B
coreml/config.json                                  947 B
coreml/multi_qa_minilm_l6_cos_v1_coreml_fp16.pte    43.4 MB
tokenizer.json                                      695 kB
tokenizer_config.json                               383 B
vulkan/config.json                                  947 B
vulkan/multi_qa_minilm_l6_cos_v1_vulkan_fp16.pte    43.1 MB
xnnpack/config.json                                 949 B
xnnpack/multi_qa_minilm_l6_cos_v1_xnnpack_fp32.pte  86.2 MB

Compatibility

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

How embedding models work

Your textsentence / documentEncodermaps meaningVectorlist of numbersAn embedding model turns text into a vector, so similar meanings sit close together, which is the basis of search and RAG.

Running it

Where it runs

Built for phones (ExecuTorch). It does not run on a GPU server.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms