BGE Small Zh V1.5 is an open-source embedding model created by BAAI. It is designed to take in text and output dense vector representations. The model is built for tasks like retrieval, classification, clustering, and semantic search, and can be used to augment large language models.
Input
Output
Context
512
Max Output
n/a
Parameters
24M
Input Modalities
Output Modalities
Some values come from web research and may be incorrect. Report incorrect data
None the catalog can show from stated facts or measured scores.
Download 0.10 GB · Runs on vLLM v0.32.0
| Precision | Weights | Smallest GPU that fits |
|---|---|---|
| FP16 / BF16 | 0.04 GB | 1x NVIDIA T4 (16 GB) |
| INT8 | 0.02 GB | 1x AMD Instinct MI455X (432 GB) |
| INT4 | 0.01 GB | 1x AMD Instinct MI455X (432 GB) |
Computed by Inferbase from the 23,954,432 parameters in the creator's Hugging Face repository; weights only, as serving adds the framework and the input being processed.
Public resources
Specification sources
As of Nov 11, 2026.
Answered from the facts on this page, with their sources.
BGE Small Zh V1.5 has a context window of 512 tokens (source: Web research). A provider may serve less; Inferbase routes on what each provider serves.
Yes. BGE Small Zh V1.5 is an open-weight model under the MIT license. You can download and self-host it within the license terms.
BGE Small Zh V1.5 has 23,954,432 parameters (24M), as stated in the creator's Hugging Face repository.
Strengths: Open weights under a permissive license (mit). Each is computed from the model's stated facts and benchmark results.
BGE Small Zh V1.5 accepts Text and produces Embedding. The Capabilities card lists the API features it supports, such as function calling and structured output.
No benchmark source has published a result for BGE Small Zh V1.5 yet, so it is shown as unmeasured, not estimated.
Not on Inferbase Managed today. Add your own provider key or endpoint that serves BGE Small Zh V1.5, and Inferbase runs it on your account with the same routing and logs.
The weights take 0.0 GB at FP16 / BF16, 0.0 GB at INT8, 0.0 GB at INT4, computed from the 23,954,432 parameters its creator publishes. Serving adds the framework and the input being processed.
The model card of BGE Small Zh V1.5 lists one language: Chinese. That is what BAAI states; the catalog does not test language quality.
Start on the free plan with 5,000 requests a month, no card required.