F2LLM 1.7B measured on 12 of 261 Embeddings benchmarks12
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
57.8MTEB English v2
Sep 2025released
2,048Dimensions
41K tokensMax input
enLanguages
Rankingconfiguration unstated?
Full ranking →···
43Stella En 400M v583.944F2LLM 1.7B83.945NV Embed v283.8Strong at
Alternatives?
ModelScoreCostPriceWhat changes
BetterQwen 3 Embedding 8BunstatedOpen+6%—$0.01Max input: 41K tokens → 33K tokens+2KOpenQZhou Embeddingunstated+9%——Max input: 41K tokens → 33K tokens+1BetterQwen 3 Embedding 0.6BunstatedOpen+3%—$0.01Max input: 41K tokens → 33K tokens+1BetterQwen 3 Embedding 4BunstatedOpen+6%—$0.02Max input: 41K tokens → 33K tokens+2
BetterJina Embeddings v5 Text NanounstatedOpen+5%—$0.02Max input: 41K tokens → 8K tokens+1ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
Qwen 3 Embedding 8BunstatedOpen+6%—$0.01Max input: 41K tokens → 33K tokens+2Qwen 3 Embedding 0.6BunstatedOpen+3%—$0.01Max input: 41K tokens → 33K tokens+1Qwen 3 Embedding 4BunstatedOpen+6%—$0.02Max input: 41K tokens → 33K tokens+2Jina Embeddings v5 Text NanounstatedOpen+5%—$0.02Max input: 41K tokens → 8K tokens+1Jina Embeddings v5 Text SmallunstatedOpen+5%—$0.05Max input: 41K tokens → 33K tokens+1ModelScoreCostPriceWhat changes
KQZhou EmbeddingunstatedOpen+9%——Max input: 41K tokens → 33K tokens+1iJasper Token Compression 600MunstatedOpen+6%——Max input: 41K tokens → 33K tokensQwen 3 Embedding 4BunstatedOpen+6%—$0.02Max input: 41K tokens → 33K tokens+2Qwen 3 Embedding 8BunstatedOpen+6%—$0.01Max input: 41K tokens → 33K tokens+2Jina Embeddings v5 Text NanounstatedOpen+5%—$0.02Max input: 41K tokens → 8K tokens+1ModelScoreCostPriceWhat changes
cF2LLM v2 8BunstatedOpensame——Memory (4-bit): 1 GB → 4.5 GBcF2LLM v2 14BunstatedOpensame——Memory (4-bit): 1 GB → 8.4 GBcF2LLM v2 1.7BunstatedOpensame——cF2LLM v2 4BunstatedOpensame——Memory (4-bit): 1 GB → 2.4 GBcF2LLM 4BunstatedOpensame——Memory (4-bit): 1 GB → 2.4 GBcF2LLM v2 0.6BunstatedOpensame——cF2LLM v2 330MunstatedOpen-1%——cF2LLM 0.6BunstatedOpen-2%——All codefuse-ai models →Run it yourself
estimateFits 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 versionsBenchmarks
in Embeddings & RetrievalFAQ
How much does F2LLM 1.7B cost?›
There is no per-unit API price: self-host only.
Is F2LLM 1.7B free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is F2LLM 1.7B, and what is it best at?›
#40 of 200 in Embeddings. Strongest at: Embeddings & Retrieval.
Is F2LLM 1.7B better than Stella En 400M v5?›
On MTEB English v2 · STS · English, F2LLM 1.7B scores 83.9 vs 83.9 — about the same.
When was F2LLM 1.7B released? Is there a newer version?›
Released 2025-09-18. It is the current version in its line.
Is F2LLM 1.7B open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run F2LLM 1.7B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is F2LLM 1.7B?›
F2LLM 1.7B is an open-weights embeddings & retrieval model from codefuse-ai, released Sep 2025.
What are the best alternatives to F2LLM 1.7B?›
Qwen 3 Embedding 8B (better), QZhou Embedding (open weights).