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 →···
137Miniac Embed83.8138F2LLM 4B83.8139Nano Em1 0.6B v283.7Strong at
Alternatives?
ModelScoreCostPriceWhat changes
BetterEmbeddingGemma 300MunstatedOpen+4%—$0.002Max input: 41K tokens → 2K tokens+1KOpenQZhou Embeddingunstated+10%——Max input: 41K tokens → 33K tokens+1
BetterBge Base En v1.5unstatedOpen+3%—$0.005Max input: 41K tokens → 1K tokensBetterBge En IclunstatedOpen+5%—$0.01Max input: 41K tokens → 33K tokens+2
BetterQwen 3 Embedding 8BunstatedOpen+4%—$0.01Max input: 41K tokens → 33K tokens+2ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
EmbeddingGemma 300MunstatedOpen+4%—$0.002Max input: 41K tokens → 2K tokens+1Bge Base En v1.5unstatedOpen+3%—$0.005Max input: 41K tokens → 1K tokensBge En IclunstatedOpen+5%—$0.01Max input: 41K tokens → 33K tokens+2Qwen 3 Embedding 8BunstatedOpen+4%—$0.01Max input: 41K tokens → 33K tokens+2Bge Large En v1.5unstatedOpen+4%—$0.01Max input: 41K tokens → 1K tokensModelScoreCostPriceWhat changes
KQZhou EmbeddingunstatedOpen+10%——Max input: 41K tokens → 33K tokens+1iJasper Token Compression 600MunstatedOpen+8%——Max input: 41K tokens → 33K tokensKNano Em1 0.6B v2.1unstatedOpen+7%——Max input: 41K tokens → 8K tokens
NV Embed v2unstatedOpen+6%——Max input: 41K tokens → 33K tokens+1aLGAI Embedding PreviewunstatedOpen+6%——Max input: 41K tokens → 33K tokens+1ModelScoreCostPriceWhat changes
cF2LLM v2 8BunstatedOpen+3%——Memory (4-bit): 2.4 GB → 4.5 GBcF2LLM v2 14BunstatedOpen+3%——Memory (4-bit): 2.4 GB → 8.4 GBcF2LLM v2 1.7BunstatedOpen+2%——cF2LLM v2 0.6BunstatedOpen+2%——cF2LLM v2 4BunstatedOpen+2%——cF2LLM v2 330MunstatedOpensame——cF2LLM 1.7BunstatedOpensame——cF2LLM v2 160MunstatedOpen-2%——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 Miniac Embed?›
On MTEB English v2 · Pair Classification · English, F2LLM 4B scores 83.8 vs 83.8 — 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?›
EmbeddingGemma 300M (better), QZhou Embedding (open weights).