KaLM Embedding Multilingual Mini Instruct v2 measured on 15 of 261 Embeddings benchmarks15
BenchmarkByScoreRank
Retrieval8
Reranking1
Other6
No benchmark matches
self-host onlyprice
86.2MTEB English v2
Jun 2025released
896Dimensions
33K tokensMax input
en, zhLanguages
Alternatives?
ModelScoreCostPriceWhat changes
BetterBge Multilingual Gemma2unstatedOpen+5%—$0.11Max input: 33K tokens → 8K tokens+2IOpenYuan Embedding 2.0 Zh+17%——Max input: 33K tokens → 1K tokens+1
BetterYoutu EmbeddingOpen+15%——Max input: 33K tokens → 1K tokens+2KBetterQZhou EmbeddingunstatedOpen+15%——Memory (4-bit): 0.3 GB → 4.2 GBTBetterConan Embedding v2unstated+14%——ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
Bge Multilingual Gemma2unstatedOpen+5%—$0.11Max input: 33K tokens → 8K tokens+2IYuan Embedding 2.0 ZhOpen+17%——Max input: 33K tokens → 1K tokens+1Youtu EmbeddingOpen+15%——Max input: 33K tokens → 1K tokens+2KQZhou EmbeddingunstatedOpen+15%——Memory (4-bit): 0.3 GB → 4.2 GBTConan Embedding v2unstated+14%——ModelScoreCostPriceWhat changes
IYuan Embedding 2.0 ZhOpen+17%——Max input: 33K tokens → 1K tokens+1Youtu EmbeddingOpen+15%——Max input: 33K tokens → 1K tokens+2KQZhou EmbeddingunstatedOpen+15%——Memory (4-bit): 0.3 GB → 4.2 GBrRitrieve Zh v1Open+12%——Max input: 33K tokens → 1K tokens+1TConan Embedding v1Open+12%——Max input: 33K tokens → 1K tokens+1ModelScoreCostPriceWhat changes
HKaLM Embedding Multilingual Mini v1unstatedOpensame——Max input: 33K tokens → 1K tokens+1HKaLM Embedding Multilingual Mini Instruct v1unstatedOpensame——Languages: not verifiedHKaLM Embedding Multilingual Mini Instruct v1.5unstatedOpensame——Languages: not verifiedAll HIT-TMG models →Run it yourself
estimateFits on✓ 8 GB (phone, laptop) · full quality✓ 16 GB · full quality✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceMITfree for commercial use
History
3 versionsBenchmarks
in Embeddings & RetrievalBEIR · Retrieval · English51.7#82
FAQ
How much does KaLM Embedding Multilingual Mini Instruct v2 cost?›
There is no per-unit API price: self-host only.
Is KaLM Embedding Multilingual Mini Instruct v2 free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is KaLM Embedding Multilingual Mini Instruct v2, and what is it best at?›
#48 of 238 in Embeddings.
Is KaLM Embedding Multilingual Mini Instruct v2 better than Harrier OSS v1 0.6B?›
On MTEB Mandarin Chinese v1 · Reranking · Mandarin Chinese, KaLM Embedding Multilingual Mini Instruct v2 scores 65.2 vs 65.5 — about the same.
When was KaLM Embedding Multilingual Mini Instruct v2 released? Is there a newer version?›
Released 2025-06-25. It is the current version in its line.
Is KaLM Embedding Multilingual Mini Instruct v2 open source?›
Yes, the weights are open (MIT licence).
Can I run KaLM Embedding Multilingual Mini Instruct v2 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is KaLM Embedding Multilingual Mini Instruct v2?›
KaLM Embedding Multilingual Mini Instruct v2 is an open-weights embeddings & retrieval model from HIT-TMG, released Jun 2025.
What are the best alternatives to KaLM Embedding Multilingual Mini Instruct v2?›
Bge Multilingual Gemma2 (better), Yuan Embedding 2.0 Zh (open weights).