self-host onlyprice
63.9ViDoRe v3
Jul 2026released
2,560Dimensions
262K tokensMax input
Alternatives?
ModelScoreCostPriceWhat changes
BetterEVIE 8BOpen+4%——Memory (4-bit): 2.7 GB → 5 GBOpenEVIE 4.5B+3%——wOpenWebAI ColVec1.1 8B+2%——Memory (4-bit): 2.7 GB → 5 GB
Openpplx Embed v2 Late 9Bsame——Max input: 262K tokens → 4K tokens+1vOpenVultronRetrieverPrime Qwen3.5 8Bsame——Memory (4-bit): 2.7 GB → 5 GBModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
EVIE 8BOpen+4%——Memory (4-bit): 2.7 GB → 5 GBRun 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/webAI-Official/webAI-ColVec1.1-4b/blob/main/LICENSE.mdno commercial use
History
2 versionsBenchmarks
in Embeddings & RetrievalFAQ
How much does WebAI ColVec1.1 4B cost?›
There is no per-unit API price: self-host only.
Is WebAI ColVec1.1 4B free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is WebAI ColVec1.1 4B, and what is it best at?›
#6 of 50 in Multimodal.
Is WebAI ColVec1.1 4B better than VultronRetrieverPrime Qwen3.5 8B?›
On ViDoRe v3 · Mean over tasks · multilingual (6 languages), WebAI ColVec1.1 4B scores 63.9 vs 64.3 — about the same.
When was WebAI ColVec1.1 4B released? Is there a newer version?›
Released 2026-07-22. It is the current version in its line.
Is WebAI ColVec1.1 4B open source?›
Yes, the weights are open (https://huggingface.co/webAI-Official/webAI-ColVec1.1-4b/blob/main/LICENSE.md licence).
Can I run WebAI ColVec1.1 4B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is WebAI ColVec1.1 4B?›
WebAI ColVec1.1 4B is an open-weights embeddings & retrieval model from webAI-Official, released Jul 2026.
What are the best alternatives to WebAI ColVec1.1 4B?›
EVIE 8B (better).