c

F2LLM v2 4B

Mar 2026
cF2LLM v2 4B
Compare in
on
self-host onlyprice
59.1MTEB English v2
Mar 2026released
2,560Dimensions
41K tokensMax input
en, es, Estonian +80Languages

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

in Embeddings & Retrieval

FAQ

How much does F2LLM v2 4B cost?›

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

Is F2LLM v2 4B free to use?›

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

How good is F2LLM v2 4B, and what is it best at?›

#29 of 200 in Embeddings. Strongest at: Embeddings & Retrieval.

Is F2LLM v2 4B better than Llama Embed Nemotron 8B?›

On MTEB Dutch v1 · Classification · Dutch, F2LLM v2 4B scores 73 vs 73.4 — about the same.

When was F2LLM v2 4B released? Is there a newer version?›

Released 2026-03-09. It is the current version in its line.

Is F2LLM v2 4B open source?›

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

Can I run F2LLM v2 4B locally?›

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

What is F2LLM v2 4B?›

F2LLM v2 4B is an open-weights embeddings & retrieval model from codefuse-ai, released Mar 2026.

What are the best alternatives to F2LLM v2 4B?›

F2LLM v2 14B (better), F2LLM v2 8B (open weights).