KaLM Embedding Multilingual Mini Instruct v1.5 measured on 30 of 194 Embeddings benchmarks30
BenchmarkByScoreRank
Retrieval5
Other25
No benchmark matches
self-host onlyprice
83.4MTEB English v2
Dec 2024released
896Dimensions
33K tokensMax input
Alternatives?
ModelScoreCostPriceWhat changes
BetterQwen 3 Embedding 8BunstatedOpen+15%—$0.01Memory (4-bit): 0.3 GB → 4.5 GBKOpenQZhou Embedding Zh+31%——Max input: 33K tokens → 8K tokens+1BetterQwen 3 Embedding 0.6BunstatedOpen+5%—$0.01Memory (4-bit): 0.3 GB → 0.4 GBBetterQwen 3 Embedding 4BunstatedOpen+14%—$0.02Memory (4-bit): 0.3 GB → 2.4 GB
BetterBge Multilingual Gemma2unstatedOpen+9%—$0.11Max input: 33K tokens → 8K tokens+1ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
Qwen 3 Embedding 8BunstatedOpen+15%—$0.01Memory (4-bit): 0.3 GB → 4.5 GBQwen 3 Embedding 0.6BunstatedOpen+5%—$0.01Memory (4-bit): 0.3 GB → 0.4 GBQwen 3 Embedding 4BunstatedOpen+14%—$0.02Memory (4-bit): 0.3 GB → 2.4 GBBge Multilingual Gemma2unstatedOpen+9%—$0.11Max input: 33K tokens → 8K tokens+1KQZhou Embedding ZhOpen+31%——Max input: 33K tokens → 8K tokens+1ModelScoreCostPriceWhat changes
KQZhou Embedding ZhOpen+31%——Max input: 33K tokens → 8K tokens+1KQZhou EmbeddingunstatedOpen+30%——Memory (4-bit): 0.3 GB → 4.2 GB
Youtu EmbeddingOpen+18%——Max input: 33K tokens → 1K tokens+1qZhinao ChineseModernBert EmbeddingOpen+18%——Max input: 33K tokens → 1K tokensrRitrieve Zh v1Open+18%——Max input: 33K tokens → 1K tokensRun 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 · English51.6#86
FAQ
How much does KaLM Embedding Multilingual Mini Instruct v1.5 cost?›
There is no per-unit API price: self-host only.
Is KaLM Embedding Multilingual Mini Instruct v1.5 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 v1.5, and what is it best at?›
#136 of 238 in Embeddings.
Is KaLM Embedding Multilingual Mini Instruct v1.5 better than KaLM Embedding Multilingual Mini Instruct v1?›
On MTEB Mandarin Chinese v1 · Pair Classification · Mandarin Chinese, KaLM Embedding Multilingual Mini Instruct v1.5 scores 72.9 vs 73.1 — about the same.
When was KaLM Embedding Multilingual Mini Instruct v1.5 released? Is there a newer version?›
Released 2024-12-26. It is the current version in its line.
Is KaLM Embedding Multilingual Mini Instruct v1.5 open source?›
Yes, the weights are open (MIT licence).
Can I run KaLM Embedding Multilingual Mini Instruct v1.5 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is KaLM Embedding Multilingual Mini Instruct v1.5?›
KaLM Embedding Multilingual Mini Instruct v1.5 is an open-weights embeddings & retrieval model from HIT-TMG, released Dec 2024.
What are the best alternatives to KaLM Embedding Multilingual Mini Instruct v1.5?›
Qwen 3 Embedding 8B (better), QZhou Embedding Zh (open weights).