pplx Embed v2 Late 9B
Oct 2026
pplx Embed v2 Late 9BCompare inonViDoRe v3
self-host onlyprice
64.8ViDoRe v3
Oct 2026released
4K tokensMax input
Alternatives?
ModelScoreCostPriceWhat changes
OpenEVIE 8B+2%——OpenEVIE 4.5Bsame——wOpenWebAI ColVec1.1 8Bsame——vOpenVultronRetrieverPrime Qwen3.5 8Bsame——wOpenWebAI ColVec1.1 4Bsame——ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
Nothing here yet.
Run it yourself
estimateFits on✓ 8 GB (phone, laptop) · compressed✓ 16 GB · 8-bit✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceMITfree for commercial use
Benchmarks
in Embeddings & RetrievalFAQ
How much does pplx Embed v2 Late 9B cost?›
There is no per-unit API price: self-host only.
Is pplx Embed v2 Late 9B free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is pplx Embed v2 Late 9B, and what is it best at?›
#4 of 50 in Multimodal.
Is pplx Embed v2 Late 9B better than WebAI ColVec1.1 8B?›
On ViDoRe v3 · Mean over tasks · multilingual (6 languages), pplx Embed v2 Late 9B scores 64.8 vs 64.9 — about the same.
When was pplx Embed v2 Late 9B released? Is there a newer version?›
Released 2026-10-05. It is the current version in its line.
Is pplx Embed v2 Late 9B open source?›
Yes, the weights are open (MIT licence).
Can I run pplx Embed v2 Late 9B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is pplx Embed v2 Late 9B?›
pplx Embed v2 Late 9B is an open-weights embeddings & retrieval model from perplexity-ai, released Oct 2026.
What are the best alternatives to pplx Embed v2 Late 9B?›
EVIE 8B (open weights).