Granite Embedding Small English R2
Aug 2025
Granite Embedding Small English R2Compare inon
Granite Embedding Small English R2 measured on 25 of 261 Embeddings benchmarks25
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
53.9MTEB English v2
Aug 2025released
384Dimensions
8K tokensMax input
enLanguages
Rankingconfiguration unstated?
Full ranking →···
29KaLM Embedding Multilingual Mini Instruct v165.130Granite Embedding Small English R263.731Snowflake Arctic Embed L v2.063.7Strong at
Alternatives?
ModelScoreCostPriceWhat changes
VBetterVoyage 3 Liteunstated+12%—$0.02Languages: not verifiedDOpenUibk Embedding v1unstated+44%——Max input: 8K tokens → 0K tokens+1
BetterJina Embeddings v5 Text SmallunstatedOpen+4%—$0.05Languages: not verified+1VBetterVoyage 3unstated+16%—$0.06Languages: not verifiedVBetterVoyage Multilingual 2unstated+24%—$0.12Languages: not verifiedModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
VVoyage 3 Liteunstated+12%—$0.02Languages: not verifiedJina Embeddings v5 Text SmallunstatedOpen+4%—$0.05Languages: not verified+1VVoyage 3unstated+16%—$0.06Languages: not verifiedVVoyage Multilingual 2unstated+24%—$0.12Languages: not verifiedVVoyage Law 2unstated+24%—$0.12Languages: not verifiedModelScoreCostPriceWhat changes
DUibk Embedding v1unstatedOpen+44%——Max input: 8K tokens → 0K tokens+1lGTE ModernColBERT v1Open+42%——Max input: 8K tokens → 0K tokens+1dUltraBERT Embed 150MunstatedOpen+24%——Memory (4-bit): 0 GB → 0.1 GBcF2LLM v2 8BunstatedOpen+20%——Memory (4-bit): 0 GB → 4.5 GBBBidirLM 1B EmbeddingOpen+20%——Max input: 8K tokens → 1K tokens+1ModelScoreCostPriceWhat changes
Granite Embedding 311M Multilingual R2unstatedOpen+13%——Memory (4-bit): 0 GB → 0.2 GBGranite Embedding English R2unstatedOpen+3%——Memory (4-bit): 0 GB → 0.1 GBGranite Embedding 97M Multilingual R2unstatedOpen+3%——Memory (4-bit): 0 GB → 0.1 GBGranite Embedding 125M EnglishunstatedOpen-34%——Max input: 8K tokens → 1K tokens+1Granite Embedding 30M EnglishunstatedOpen-40%——Max input: 8K tokens → 1K tokensGranite Embedding 278M MultilingualunstatedOpen-41%——Max input: 8K tokens → 1K tokens+1Granite Embedding 107M MultilingualunstatedOpen-46%——Max input: 8K tokens → 1K tokens+1All IBM 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
LicenceApache-2.0free for commercial use
Benchmarks
in Embeddings & RetrievalBEIR · Retrieval · English50.9#95
FAQ
How much does Granite Embedding Small English R2 cost?›
There is no per-unit API price: self-host only.
Is Granite Embedding Small English R2 free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Granite Embedding Small English R2, and what is it best at?›
#69 of 200 in Embeddings.
Is Granite Embedding Small English R2 better than KaLM Embedding Multilingual Mini Instruct v1?›
On LongEmbed · Mean over tasks · English, Granite Embedding Small English R2 scores 63.7 vs 65.1 — lower.
When was Granite Embedding Small English R2 released? Is there a newer version?›
Released 2025-08-15. It is the current version in its line.
Is Granite Embedding Small English R2 open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Granite Embedding Small English R2 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Granite Embedding Small English R2?›
Granite Embedding Small English R2 is an open-weights embeddings & retrieval model from IBM, released Aug 2025.
What are the best alternatives to Granite Embedding Small English R2?›
Voyage 3 Lite (better), Uibk Embedding v1 (open weights).