Colpali v1.3 measured on 8 of 203 Multimodal benchmarks8
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
79.4MIEB lite
Nov 2024released
16K tokensMax input
enLanguages
Ranking?
Full ranking →···
34Colqwen2 v1.044.735Colpali v1.343.136BiUltraVBERT31.7Strong at
Alternatives?
ModelScoreCostPriceWhat changes
BetterNemotron 3.5 Embed 1B BF16Open+34%—$0.015
OpenEVIE 8B+54%——Languages: not verified+1
BetterJina Embeddings v5 Omni NanounstatedOpen+6%—$0.02Max input: 16K tokens → 8K tokens+1BetterNemotron 3.5 Embed 8B BF16Open+40%—$0.035Memory (4-bit): 1.8 GB → 5 GBBetterJina Embeddings v5 Omni SmallunstatedOpen+6%—$0.05Languages: not verifiedModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
Nemotron 3.5 Embed 1B BF16Open+34%—$0.015Jina Embeddings v5 Omni NanounstatedOpen+6%—$0.02Max input: 16K tokens → 8K tokens+1Nemotron 3.5 Embed 8B BF16Open+40%—$0.035Memory (4-bit): 1.8 GB → 5 GBJina Embeddings v5 Omni SmallunstatedOpen+6%—$0.05Languages: not verified
Qwen 3 VL Embedding 8BOpen+34%—$0.09Languages: not verified+1ModelScoreCostPriceWhat changes
EVIE 8BOpen+54%——Languages: not verified+1EVIE 4.5BOpen+53%——Languages: not verified+1wWebAI ColVec1.1 8BOpen+51%——Languages: not verified+1
pplx Embed v2 Late 9BOpen+50%——Max input: 16K tokens → 4K tokens+2vVultronRetrieverPrime Qwen3.5 8BOpen+49%——Memory (4-bit): 1.8 GB → 5 GBRun 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 & RetrievalMMEB-V2lab44.2
FAQ
How much does Colpali v1.3 cost?›
There is no per-unit API price: self-host only.
Is Colpali v1.3 free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Colpali v1.3, and what is it best at?›
#36 of 89 in Multimodal.
Is Colpali v1.3 better than Colqwen2 v1.0?›
On ViDoRe v3 · Mean over tasks · multilingual (6 languages), Colpali v1.3 scores 43.1 vs 44.7 — lower.
When was Colpali v1.3 released? Is there a newer version?›
Released 2024-11-01. It is the current version in its line.
Is Colpali v1.3 open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Colpali v1.3 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Colpali v1.3?›
Colpali v1.3 is an open-weights embeddings & retrieval model from vidore, released Nov 2024.
What are the best alternatives to Colpali v1.3?›
Nemotron 3.5 Embed 1B BF16 (better), EVIE 8B (open weights).