EvoQwen2.5 VL Retriever 3B v1 measured on 4 of 203 Multimodal benchmarks4
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
86.7MIEB lite
Nov 2025released
2,048Dimensions
128K tokensMax input
enLanguages
Ranking?
Full ranking →···
21WebAI ColVec1 4B86.922EvoQwen2.5 VL Retriever 3B v186.723ColNanoVDR Q Ettin150M ColVec4B 640 ML86.5Strong at
Alternatives?
ModelScoreCostPriceWhat changes
DBetterArgus Colqwen3.5 9B v0unstatedOpen+3%——Max input: 128K tokens → 33K tokens+1
BetterNemotron Colembed VL 8B v2Open+3%——Languages: not verified+1DBetterArgus Colqwen3.5 4B v0unstatedOpen+3%——Max input: 128K tokens → 33K tokens+1vBetterVultronRetrieverPrime Qwen3.5 8BOpen+3%——Memory (4-bit): 1.8 GB → 5 GBvBetterVultronRetrieverCore Qwen3.5 4.5BOpen+2%——Memory (4-bit): 1.8 GB → 2.7 GBModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
DArgus Colqwen3.5 9B v0unstatedOpen+3%——Max input: 128K tokens → 33K tokens+1Nemotron Colembed VL 8B v2Open+3%——Languages: not verified+1DArgus Colqwen3.5 4B v0unstatedOpen+3%——Max input: 128K tokens → 33K tokens+1vVultronRetrieverPrime Qwen3.5 8BOpen+3%——Memory (4-bit): 1.8 GB → 5 GBvVultronRetrieverCore Qwen3.5 4.5BOpen+2%——Memory (4-bit): 1.8 GB → 2.7 GBModelScoreCostPriceWhat changes
DArgus Colqwen3.5 9B v0unstatedOpen+3%——Max input: 128K tokens → 33K tokens+1Nemotron Colembed VL 8B v2Open+3%——Languages: not verified+1DArgus Colqwen3.5 4B v0unstatedOpen+3%——Max input: 128K tokens → 33K tokens+1vVultronRetrieverPrime Qwen3.5 8BOpen+3%——Memory (4-bit): 1.8 GB → 5 GBvVultronRetrieverCore Qwen3.5 4.5BOpen+2%——Memory (4-bit): 1.8 GB → 2.7 GBModelScoreCostPriceWhat changes
AEvoQwen2.5 VL Retriever 7B v1Opensame——Memory (4-bit): 1.8 GB → 4.2 GBAll ApsaraStackMaaS 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
LicenceApache-2.0free for commercial use
Benchmarks
in Embeddings & RetrievalFAQ
How much does EvoQwen2.5 VL Retriever 3B v1 cost?›
There is no per-unit API price: self-host only.
Is EvoQwen2.5 VL Retriever 3B v1 free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is EvoQwen2.5 VL Retriever 3B v1, and what is it best at?›
#22 of 89 in Multimodal. Strongest at: Embeddings & Retrieval.
Is EvoQwen2.5 VL Retriever 3B v1 better than WebAI ColVec1 4B?›
On MIEB lite · Document Understanding · English, EvoQwen2.5 VL Retriever 3B v1 scores 86.7 vs 86.9 — about the same.
When was EvoQwen2.5 VL Retriever 3B v1 released? Is there a newer version?›
Released 2025-11-04. It is the current version in its line.
Is EvoQwen2.5 VL Retriever 3B v1 open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run EvoQwen2.5 VL Retriever 3B v1 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is EvoQwen2.5 VL Retriever 3B v1?›
EvoQwen2.5 VL Retriever 3B v1 is an open-weights embeddings & retrieval model from ApsaraStackMaaS, released Nov 2025.
What are the best alternatives to EvoQwen2.5 VL Retriever 3B v1?›
Argus Colqwen3.5 9B v0 (better).