j

FollowIR 7B

Apr 2024
jFollowIR 7B
Compare in
on
price not verifiedprice
—main score
Apr 2024released
33K tokensMax input
enLanguages

Ranking?

Not ranked yet: no results on a category benchmark.

Alternatives?

ModelScoreCostPriceWhat changes
cOpenMonot5 3B Msmarco 10K-79%——Max input: not verified+1cOpenMonot5 Base Msmarco 10K-114%——Max input: not verified+1

Run it yourself

estimate
Fits 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
LicenceApache-2.0free for commercial use

Benchmarks

all categories
Embeddings & Retrieval
MTEB Europe v1 · Instruction Reranking · English12.2#1
FollowIR · Mean over tasks · English12.2#1
FollowIR · Mean over task types · English12.2#1
FollowIR · Instruction Reranking · English12.2#1
MTEB multilingual v2 · Instruction Reranking · English12.2#1

FAQ

How much does FollowIR 7B cost?›

There is no per-unit API price: price not verified.

Is FollowIR 7B better than Qwen 3 Embedding 4B?›

On FollowIR · Mean over tasks · English, FollowIR 7B scores 12.2 vs 11.6 — about the same.

When was FollowIR 7B released? Is there a newer version?›

Released 2024-04-29. It is the current version in its line.

Is FollowIR 7B open source?›

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

Can I run FollowIR 7B locally?›

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

What is FollowIR 7B?›

FollowIR 7B is an open-weights embeddings & retrieval model from jhu-clsp, released Apr 2024.

What are the best alternatives to FollowIR 7B?›

Monot5 3B Msmarco 10K (open weights).