LLM2Vec Sheared Llama Mntp Unsup Simcse measured on 6 of 261 Embeddings benchmarks6
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
72.2MTEB English v2
Apr 2024released
33K tokensMax input
enLanguages
Alternatives?
ModelScoreCostPriceWhat changes
BetterBge Base En v1.5unstatedOpen×2.1—$0.005Max input: 33K tokens → 1K tokens
OpenNV Embed v2unstated×2.4——Memory (4-bit): 0.8 GB → 4.7 GBtBetterGte BaseunstatedOpen+97%—$0.005Max input: 33K tokens → 1K tokensiBetterE5 Base v2unstatedOpen+94%—$0.005Max input: 33K tokens → 1K tokenssBetterAll Mpnet Base v2unstatedOpen+69%—$0.005Max input: 33K tokens → 0K tokensModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
Bge Base En v1.5unstatedOpen×2.1—$0.005Max input: 33K tokens → 1K tokenstGte BaseunstatedOpen+97%—$0.005Max input: 33K tokens → 1K tokensiE5 Base v2unstatedOpen+94%—$0.005Max input: 33K tokens → 1K tokenssAll Mpnet Base v2unstatedOpen+69%—$0.005Max input: 33K tokens → 0K tokenssAll MiniLM L12 v2unstatedOpen+65%—$0.005Max input: 33K tokens → 0K tokensModelScoreCostPriceWhat changes
NV Embed v2unstatedOpen×2.4——Memory (4-bit): 0.8 GB → 4.7 GB
Qwen 3 Embedding 8BunstatedOpen×2.4—$0.01Languages: not verified+1Bge En IclunstatedOpen×2.4—$0.01Languages: not verified+1yLENS D8000unstatedOpen×2.4——Languages: not verified+1iInf Retriever v1unstatedOpen×2.4——Memory (4-bit): 0.8 GB → 4.2 GBModelScoreCostPriceWhat changes
MLLM2Vec Meta Llama 3 8B Instruct Mntp SupervisedunstatedOpen×2.2——Max input: 33K tokens → 8K tokens+1MLLM2Vec Mistral 7B Instruct v2 Mntp SupervisedunstatedOpen×2.2——Memory (4-bit): 0.8 GB → 4.3 GBMLLM2Vec Llama 2 7B Chat Hf Mntp SupervisedunstatedOpen×2.1——Memory (4-bit): 0.8 GB → 4 GBMLLM2Vec Sheared Llama Mntp SupervisedunstatedOpen+98%——MLLM2Vec Meta Llama 3 8B Instruct Mntp Unsup SimcseunstatedOpen+51%——Max input: 33K tokens → 8K tokens+1MLLM2Vec Mistral 7B Instruct v2 Mntp Unsup SimcseunstatedOpen+47%——Memory (4-bit): 0.8 GB → 4.3 GBMLLM2Vec Llama 2 7B Chat Hf Mntp Unsup SimcseunstatedOpen+42%——Memory (4-bit): 0.8 GB → 4 GBAll McGill-NLP 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
Benchmarks
in Embeddings & RetrievalBEIR · Mean over tasks · English25.9#173
BEIR · Retrieval · English25.9#173
FAQ
How much does LLM2Vec Sheared Llama Mntp Unsup Simcse cost?›
There is no per-unit API price: self-host only.
Is LLM2Vec Sheared Llama Mntp Unsup Simcse free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is LLM2Vec Sheared Llama Mntp Unsup Simcse, and what is it best at?›
#222 of 238 in Embeddings.
Is LLM2Vec Sheared Llama Mntp Unsup Simcse better than Squirtle?›
On BEIR · Mean over task types · English, LLM2Vec Sheared Llama Mntp Unsup Simcse scores 25.9 vs 26.2 — about the same.
When was LLM2Vec Sheared Llama Mntp Unsup Simcse released? Is there a newer version?›
Released 2024-04-09. It is the current version in its line.
Is LLM2Vec Sheared Llama Mntp Unsup Simcse open source?›
Yes, the weights are open (MIT licence).
Can I run LLM2Vec Sheared Llama Mntp Unsup Simcse locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is LLM2Vec Sheared Llama Mntp Unsup Simcse?›
LLM2Vec Sheared Llama Mntp Unsup Simcse is an open-weights embeddings & retrieval model from McGill-NLP, released Apr 2024.
What are the best alternatives to LLM2Vec Sheared Llama Mntp Unsup Simcse?›
Bge Base En v1.5 (better), NV Embed v2 (open weights).