c

F2LLM 0.6B

Sep 2025
cF2LLM 0.6B
Compare in
on
self-host onlyprice
55.7MTEB English v2
Sep 2025released
1,024Dimensions
41K tokensMax input
enLanguages

Rankingconfiguration unstated?

Full ranking →
1C2LLM 7B60.12F2LLM v2 330M60.13F2LLM v2 1.7B59.64Splade Code 8B59.65F2LLM v2 14B59.6
···
14Qwen 3 Embedding 4B56.515F2LLM 0.6B56.216F2LLM v2 80M55.8

Strong at

B
Embeddings & Retrieval#52 of 200

Alternatives?

ModelScoreCostPriceWhat changes
BetterQwen 3 Embedding 8BunstatedOpen+5%—$0.01Max input: 41K tokens → 33K tokens+2cOpenC2LLM 7B+7%——Max input: 41K tokens → 33K tokens+1cBetterF2LLM v2 330MunstatedOpen+7%——cBetterF2LLM v2 1.7BunstatedOpen+6%——Memory (4-bit): 0.4 GB → 1 GBnBetterSplade Code 8BOpen+6%——Languages: not verified+1

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

History

2 versions
5657585960Oct 25Jan 26Release dateCoREB v1 (task avg)0.6Bv2
5657585960Oct 25Jan 26Release dateCoREB v1 (task avg)0.6Bv2

Benchmarks

in Embeddings & Retrieval
MTEB Medical v1 · Clustering · English54.9#6
MTEB Thai v1 · Mean over tasks · multilingual (2 languages)54.3#24
MTEB Thai v1 · Mean over task types · multilingual (2 languages)52.6#24
MTEB Thai v1 · Clustering · Thai38.4#82
MTEB Thai v1 · Classification · Thai66.5#13
MTEB Thai v1 · Pair Classification · Thai68.8#62
MTEB Thai v1 · Retrieval · multilingual (2 languages)52.6#25
MTEB Thai v1 · Reranking · Thai36.6#27
CoREB v1 · Mean over tasks · multilingual (6 languages)56.2#15
CoREB v1 · Mean over task types · multilingual (6 languages)56.2#15
CoREB v1 · Reranking · multilingual (6 languages)52.5#15
CoREB v1 · Retrieval · multilingual (6 languages)59.9#15

FAQ

How much does F2LLM 0.6B cost?›

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

Is F2LLM 0.6B free to use?›

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

How good is F2LLM 0.6B, and what is it best at?›

#52 of 200 in Embeddings.

Is F2LLM 0.6B better than Qwen 3 Embedding 4B?›

On CoREB v1 · Mean over tasks · multilingual (6 languages), F2LLM 0.6B scores 56.2 vs 56.5 — about the same.

When was F2LLM 0.6B released? Is there a newer version?›

Released 2025-09-18. It is the current version in its line.

Is F2LLM 0.6B open source?›

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

Can I run F2LLM 0.6B locally?›

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

What is F2LLM 0.6B?›

F2LLM 0.6B is an open-weights embeddings & retrieval model from codefuse-ai, released Sep 2025.

What are the best alternatives to F2LLM 0.6B?›

Qwen 3 Embedding 8B (better), C2LLM 7B (open weights).