Llama Nemoretriever Colembed 3B v1
Jun 2025
Llama Nemoretriever Colembed 3B v1Compare inon
Llama Nemoretriever Colembed 3B v1 measured on 5 of 203 Multimodal benchmarks5
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
88MIEB lite
Jun 2025released
8K tokensMax input
Ranking?
Full ranking →···
12SauerkrautLM ColQwen3 8B v0.191.113Llama Nemoretriever Colembed 3B v19114SauerkrautLM ColQwen3 4B v0.190.8Strong at
Alternatives?
ModelScoreCostPriceWhat changes
DOpenArgus Colqwen3.5 9B v0unstated+2%——Memory (4-bit): 2.6 GB → 5.3 GBOpenNemotron Colembed VL 8B v2+2%——Memory (4-bit): 2.6 GB → 5.2 GBDOpenArgus Colqwen3.5 4B v0unstated+1%——Memory (4-bit): 2.6 GB → 2.8 GBvOpenVultronRetrieverCore Qwen3.5 4.5B+1%——Memory (4-bit): 2.6 GB → 2.7 GBvOpenVultronRetrieverPrime Qwen3.5 8B+1%——Memory (4-bit): 2.6 GB → 5 GBModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
DArgus Colqwen3.5 9B v0unstatedOpen+2%——Memory (4-bit): 2.6 GB → 5.3 GBNemotron Colembed VL 8B v2Open+2%——Memory (4-bit): 2.6 GB → 5.2 GBDArgus Colqwen3.5 4B v0unstatedOpen+1%——Memory (4-bit): 2.6 GB → 2.8 GBvVultronRetrieverCore Qwen3.5 4.5BOpen+1%——Memory (4-bit): 2.6 GB → 2.7 GBvVultronRetrieverPrime Qwen3.5 8BOpen+1%——Memory (4-bit): 2.6 GB → 5 GBModelScoreCostPriceWhat changes
Nemotron Colembed VL 8B v2Open+2%——Memory (4-bit): 2.6 GB → 5.2 GBLlama Nemotron Colembed VL 3B v2Opensame——Nemotron Colembed VL 4B v2Opensame——Memory (4-bit): 2.6 GB → 2.9 GBLlama Nemoretriever Colembed 1B v1Opensame——Nemotron 3.5 Embed 1B BF16Openn/a—$0.015Nemotron 3.5 Embed 8B BF16Openn/a—$0.035Memory (4-bit): 2.6 GB → 5 GBLlama Nemotron Embed VL 1B v2Openn/a—$0.01Omni Embed Nemotron 3BOpenn/a——Memory (4-bit): 2.6 GB → 2.8 GBAll NVIDIA models →Run it yourself
estimateFits on✓ 8 GB (phone, laptop) · 8-bit✓ 16 GB · full quality✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
Licencehttps://huggingface.co/nvidia/llama-nemoretriever-colembed-1b-v1/blob/main/LICENSEcommercial use with conditions
Benchmarks
in Embeddings & RetrievalFAQ
How much does Llama Nemoretriever Colembed 3B v1 cost?›
There is no per-unit API price: self-host only.
Is Llama Nemoretriever Colembed 3B v1 free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Llama Nemoretriever Colembed 3B v1, and what is it best at?›
#10 of 89 in Multimodal. Strongest at: Embeddings & Retrieval.
Is Llama Nemoretriever Colembed 3B v1 better than SauerkrautLM ColQwen3 8B v0.1?›
On MIEB multilingual · Document Understanding · English, Llama Nemoretriever Colembed 3B v1 scores 91 vs 91.1 — about the same.
When was Llama Nemoretriever Colembed 3B v1 released? Is there a newer version?›
Released 2025-06-27. It is the current version in its line.
Is Llama Nemoretriever Colembed 3B v1 open source?›
Yes, the weights are open (https://huggingface.co/nvidia/llama-nemoretriever-colembed-1b-v1/blob/main/LICENSE licence).
Can I run Llama Nemoretriever Colembed 3B v1 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Llama Nemoretriever Colembed 3B v1?›
Llama Nemoretriever Colembed 3B v1 is an open-weights embeddings & retrieval model from NVIDIA, released Jun 2025.
What are the best alternatives to Llama Nemoretriever Colembed 3B v1?›
Argus Colqwen3.5 9B v0 (open weights).