skip to content
gigarouter gigarouter
models / embeddings · coming soon

KaLM Embedding Multilingual Mini Instruct V1

HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1

published Oct 2024 · updated Mar 2025

KaLM Embedding Multilingual Mini Instruct V1 is a multilingual embedding model adapted from Qwen2-0.5B that supports instruction-based queries for tasks like retrieval, classification, and clustering.

est. price
~$0.008
/ 1M tokens · estimated, set at launch
API providers
0
downloads / mo
732
license
mit

specs

TaskEmbedding
ArchitectureAdapted auto-regressive LLM (Qwen2-0.5B) with mean pooling
Parameters494M
LicenseMIT
Max Sequence Length512 tokens
Instruction SupportYes (for classification and clustering)

best for

FAQ

What is this model best for?

It is best for multilingual embedding tasks such as retrieval, classification, and clustering, with optional instruction prompts for classification and clustering.

How does it compare to other multilingual embedding models?

It outperforms similar-sized models like multilingual-e5-large and bge-m3 on the MTEB benchmark, achieving an average score of 64.16.

What is the input and output format?

Input is text strings; output is normalized embedding vectors (dense). The model supports a prompt prefix for instruction tasks and a max sequence length of 512 tokens.

How do I call this model via the gigarouter API?

Use the gigarouter OpenAI-compatible endpoint with your API key. Send a request with the model name and input text to get the embedding vector.

What license does this model use?

The KaLM-Embedding repository is released under the MIT license, allowing free use, modification, and distribution.

not yet live

We're benchmarking and onboarding KaLM Embedding Multilingual Mini Instruct V1 as a hosted, OpenAI-compatible API. Sign in for free credit and be ready when it lands, or tell us you want it and we'll prioritize it.

related embeddings models

compare all →