v

VultronRetrieverFlash Qwen3.5 0.8B

Jun 2026
vVultronRetrieverFlash Qwen3.5 0.8B
Compare in
on
self-host onlyprice
83.7MIEB lite
Jun 2026released
262K tokensMax input
en, es, fr +3Languages

Ranking?

Full ranking →
1Argus Colqwen3.5 9B v092.72Nemotron Colembed VL 8B v292.73Argus Colqwen3.5 4B v092.34VultronRetrieverCore Qwen3.5 4.5B92.25VultronRetrieverPrime Qwen3.5 8B92.1
···
29SauerkrautLM ColQwen3 1.7B Turbo v0.188.930VultronRetrieverFlash Qwen3.5 0.8B88.231ColUltraVBERT86.4

Strong at

B
Embeddings & Retrieval#30 of 89

Alternatives?

ModelScoreCostPriceWhat changes
BetterJina Embeddings v4unstatedOpen+2%—$0.05Max input: 262K tokens → 128K tokens+2DOpenArgus Colqwen3.5 9B v0unstated+5%——Max input: 262K tokens → 33K tokens+2BetterNemotron Colembed VL 8B v2Open+5%——Languages: not verified+1DBetterArgus Colqwen3.5 4B v0unstatedOpen+5%——Max input: 262K tokens → 33K tokens+2vBetterVultronRetrieverCore Qwen3.5 4.5BOpen+5%——Memory (4-bit): 0.5 GB → 2.7 GB

Run it yourself

estimate
Fits 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 & Retrieval
MIEB English · Document Understanding · English88.2#30
MIEB lite · Document Understanding · English83.7#30
MIEB multilingual · Document Understanding · English88.2#30
ViDoRe v3 · Mean over tasks · multilingual (6 languages)56.2#25
ViDoRe v1&v2 · Mean over tasks · multilingual (4 languages)80.2#27

FAQ

How much does VultronRetrieverFlash Qwen3.5 0.8B cost?›

There is no per-unit API price: self-host only.

Is VultronRetrieverFlash Qwen3.5 0.8B free to use?›

There is no free API. The weights are open, so you can run it yourself.

How good is VultronRetrieverFlash Qwen3.5 0.8B, and what is it best at?›

#30 of 89 in Multimodal.

Is VultronRetrieverFlash Qwen3.5 0.8B better than SauerkrautLM ColQwen3 1.7B Turbo v0.1?›

On MIEB multilingual · Document Understanding · English, VultronRetrieverFlash Qwen3.5 0.8B scores 88.2 vs 88.9 — about the same.

When was VultronRetrieverFlash Qwen3.5 0.8B released? Is there a newer version?›

Released 2026-06-21. It is the current version in its line.

Is VultronRetrieverFlash Qwen3.5 0.8B open source?›

Yes, the weights are open (Apache-2.0 licence).

Can I run VultronRetrieverFlash Qwen3.5 0.8B locally?›

The weights are open and can be self-hosted; hardware needs are not confirmed yet.

What is VultronRetrieverFlash Qwen3.5 0.8B?›

VultronRetrieverFlash Qwen3.5 0.8B is an open-weights embeddings & retrieval model from vultr, released Jun 2026.

What are the best alternatives to VultronRetrieverFlash Qwen3.5 0.8B?›

Jina Embeddings v4 (better), Argus Colqwen3.5 9B v0 (open weights).