Store › model › Embeddings
mxbai-embed-xsmall-v1
by mixedbread-ai · source Hugging Face · updated 2025-03-13
apache-2.029 MB~1 GB RAMsource aliveunlabeled
<path fill="#e94c28" d="M922 537c-6.003 11.784-11.44 23.81-19.66 34.428-6.345 8.196-11.065 17.635-17.206 26.008-4.339 5.916-9.828 10.992-14.854 16.397-.776.835-1.993 1.279-2.71 2.147-9.439 11.437-22.…
Add to LogiShell Open in the web IDE
The button opens LogiShell with this card; nothing installs from a link by itself. Inside the app the install goes through lsh models install hf:mixedbread-ai/mxbai-embed-xsmall-v1 and its progress lives in the Resource Center.
Source and license
- Source: https://huggingface.co/mixedbread-ai/mxbai-embed-xsmall-v1
- License: apache-2.0
- Requirements: about 1 GB of RAM, 29 MB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with llama.cpp.
- Tags:
sentence-transformersonnxsafetensorsopenvinoggufbertmtebfeature-extractionenmodel-indextext-embeddings-inferenceendpoints_compatible
Numbers
- 26,435 downloads on Hugging Face
- 37 likes
- license apache-2.0
- 0.0 GB for gguf/mxbai-embed-xsmall-v1-q8_0.gguf
- 4,402,710 npm downloads a week for @huggingface/transformers
- latest @huggingface/transformers@4.3.0
Numbers as of 2026-10-02 21:01 UTC, from the source API.
Summary
Summary not ready yet: the numbers are here, the text is not. It is written by the collector through the LogiShell model facade when a provider key is present.
Reviews
No reviews yet. Reviews are written inside LogiShell: open this card in the app.
Files
| file | quant | size |
|---|---|---|
gguf/mxbai-embed-xsmall-v1-bf16.gguf | BF16 | 49 MB |
gguf/mxbai-embed-xsmall-v1-f16.gguf | F16 | 49 MB |
gguf/mxbai-embed-xsmall-v1-f32.gguf | F32 | 92 MB |
gguf/mxbai-embed-xsmall-v1-q8_0.gguf | Q8_0 | 29 MB |
model.safetensors | 46 MB | |
onnx/model.onnx | 92 MB | |
onnx/model_bnb4.onnx | 57 MB | |
onnx/model_fp16.onnx | 46 MB | |
onnx/model_int8.onnx | 23 MB | |
onnx/model_q4.onnx | 57 MB | |
onnx/model_q4f16.onnx | F16 | 31 MB |
onnx/model_quantized.onnx | 23 MB | |
onnx/model_uint8.onnx | 23 MB | |
openvino/openvino_model.bin | 91 MB | |
openvino/openvino_model_qint8_quantized.bin | 23 MB |
From the source README
<path fill="#e94c28" d="M922 537c-6.003 11.784-11.44 23.81-19.66 34.428-6.345 8.196-11.065 17.635-17.206 26.008-4.339 5.916-9.828 10.992-14.854 16.397-.776.835-1.993 1.279-2.71 2.147-9.439 11.437-22.008 18.427-35.357 24.
Source: https://huggingface.co/mixedbread-ai/mxbai-embed-xsmall-v1
Card id model:hf:mixedbread-ai/mxbai-embed-xsmall-v1 · collected 2026-10-02 21:01 UTC · JSON