F2LLM 4B measured on 8 of 194 Embeddings benchmarks8
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
59.6MTEB English v2
Sep 2025released
2,560Dimensions
41K tokensMax input
enLanguages
Rankingconfiguration unstated?
Full ranking →···
26Giga Embeddings Instruct59.727F2LLM 4B59.628Giga Embeddings Instruct 3B 082659.4Strong at
Alternatives?
ModelScoreCostPriceWhat changes
BetterQwen 3 Embedding 8BunstatedOpen+16%—$0.01Max input: 41K tokens → 33K tokens+2IOpenYuan Embedding 2.0 Enunstated+19%——Max input: 41K tokens → 33K tokensBetterQwen 3 Embedding 0.6BunstatedOpen+4%—$0.01Max input: 41K tokens → 33K tokens+1BetterQwen 3 Embedding 4BunstatedOpen+15%—$0.02Max input: 41K tokens → 33K tokens+1
BetterGemini Embedding 001unstated+8%—$0.15Max input: 41K tokens → 2K tokensModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
Qwen 3 Embedding 8BunstatedOpen+16%—$0.01Max input: 41K tokens → 33K tokens+2Qwen 3 Embedding 0.6BunstatedOpen+4%—$0.01Max input: 41K tokens → 33K tokens+1Qwen 3 Embedding 4BunstatedOpen+15%—$0.02Max input: 41K tokens → 33K tokens+1Gemini Embedding 001unstated+8%—$0.15Max input: 41K tokens → 2K tokensIYuan Embedding 2.0 EnunstatedOpen+19%——Max input: 41K tokens → 33K tokensModelScoreCostPriceWhat changes
IYuan Embedding 2.0 EnunstatedOpen+19%——Max input: 41K tokens → 33K tokensQwen 3 Embedding 8BunstatedOpen+16%—$0.01Max input: 41K tokens → 33K tokens+2Qwen 3 Embedding 4BunstatedOpen+15%—$0.02Max input: 41K tokens → 33K tokens+1KQZhou EmbeddingunstatedOpen+13%——Max input: 41K tokens → 33K tokens+1iJasper Token Compression 600MunstatedOpen+11%——Max input: 41K tokens → 33K tokensModelScoreCostPriceWhat changes
cF2LLM v2 14BunstatedOpen+2%——Memory (4-bit): 2.4 GB → 8.4 GBcF2LLM v2 8BunstatedOpensame——Memory (4-bit): 2.4 GB → 4.5 GBcF2LLM v2 4BunstatedOpensame——cF2LLM 1.7BunstatedOpen-3%——cF2LLM v2 1.7BunstatedOpen-5%——cF2LLM 0.6BunstatedOpen-7%——cF2LLM v2 0.6BunstatedOpen-9%——cF2LLM v2 330MunstatedOpen-11%——All codefuse-ai models →Run it yourself
estimateFits 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
History
2 versionsBenchmarks
in Embeddings & RetrievalFAQ
How much does F2LLM 4B cost?›
There is no per-unit API price: self-host only.
Is F2LLM 4B free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is F2LLM 4B, and what is it best at?›
#25 of 200 in Embeddings. Strongest at: Embeddings & Retrieval.
Is F2LLM 4B better than Giga Embeddings Instruct?›
On MTEB English v2 · Retrieval · English, F2LLM 4B scores 59.6 vs 59.7 — about the same.
When was F2LLM 4B released? Is there a newer version?›
Released 2025-09-18. It is the current version in its line.
Is F2LLM 4B open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run F2LLM 4B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is F2LLM 4B?›
F2LLM 4B is an open-weights embeddings & retrieval model from codefuse-ai, released Sep 2025.
What are the best alternatives to F2LLM 4B?›
Qwen 3 Embedding 8B (better), Yuan Embedding 2.0 En (open weights).