Colpali v1.2 measured on 7 of 203 Multimodal benchmarks7
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
78.4MIEB lite
Aug 2024released
16K tokensMax input
enLanguages
Ranking?
Full ranking →···
39SauerkrautLM ColLFM2 450M v0.178.940Colpali v1.278.441E5 Omni 3B78.3Strong at
Alternatives?
ModelScoreCostPriceWhat changes
ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
ModelScoreCostPriceWhat changes
DArgus Colqwen3.5 9B v0unstatedOpen+14%——Memory (4-bit): 1.8 GB → 5.3 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
History
3 versionsBenchmarks
in Embeddings & RetrievalFAQ
How much does Colpali v1.2 cost?›
There is no per-unit API price: self-host only.
Is Colpali v1.2 free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Colpali v1.2, and what is it best at?›
#40 of 89 in Multimodal.
Is Colpali v1.2 better than SauerkrautLM ColLFM2 450M v0.1?›
On MIEB lite · Document Understanding · English, Colpali v1.2 scores 78.4 vs 78.9 — about the same.
When was Colpali v1.2 released? Is there a newer version?›
Released 2024-08-26. It is the current version in its line.
Is Colpali v1.2 open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Colpali v1.2 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Colpali v1.2?›
Colpali v1.2 is an open-weights embeddings & retrieval model from vidore, released Aug 2024.
What are the best alternatives to Colpali v1.2?›
Jina Embeddings v4 (better), Argus Colqwen3.5 9B v0 (open weights).