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
VBetterVoyage 3 M Expunstated+8%——Max input: 33K tokens → 32K tokens+1cOpenF2LLM 4Bunstated+3%——Languages: loses zh+1cBetterF2LLM v2 14BunstatedOpen+3%——Memory (4-bit): 0.3 GB → 8.4 GBcBetterF2LLM v2 4BunstatedOpen+3%——Memory (4-bit): 0.3 GB → 2.4 GBaBetterGiga Embeddings Instruct 10B A1.8B 0826unstatedOpen+3%——Max input: 33K tokens → 8K tokens+1ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
VVoyage 3 M Expunstated+8%——Max input: 33K tokens → 32K tokens+1cF2LLM v2 14BunstatedOpen+3%——Memory (4-bit): 0.3 GB → 8.4 GBcF2LLM 4BunstatedOpen+3%——Languages: loses zh+1cF2LLM v2 4BunstatedOpen+3%——Memory (4-bit): 0.3 GB → 2.4 GBaGiga Embeddings Instruct 10B A1.8B 0826unstatedOpen+3%——Max input: 33K tokens → 8K tokens+1ModelScoreCostPriceWhat changes
cF2LLM 4BunstatedOpen+3%——Languages: loses zh+1cF2LLM v2 4BunstatedOpen+3%——Memory (4-bit): 0.3 GB → 2.4 GBaGiga Embeddings Instruct 10B A1.8B 0826unstatedOpen+3%——Max input: 33K tokens → 8K tokens+1cF2LLM v2 8BunstatedOpen+3%——Memory (4-bit): 0.3 GB → 4.5 GBaGiga Embeddings Instruct 3B 0826unstatedOpen+3%——Max input: 33K tokens → 8K tokens+1ModelScoreCostPriceWhat changes
HKaLM Embedding Multilingual Mini Instruct v1.5unstatedOpen-3%——Languages: not verifiedHKaLM Embedding Multilingual Mini Instruct v1unstatedOpen-7%——Languages: not verifiedHKaLM Embedding Multilingual Mini v1unstatedOpen-13%——Max input: 33K tokens → 1K tokens+1All 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 EmbeddingGemma 2?›
On MTEB English v2 · Classification · English, KaLM Embedding Multilingual Mini Instruct v2 scores 88.8 vs 88.8 — 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?›
Voyage 3 M Exp (better), F2LLM 4B (open weights).