F2LLM v2 14B vs F2LLM v2 8B
MTEB multilingual v2 · Mean over tasks · multilingual (1037 languages) Embeddings assign examples to categories, group similar examples, estimate semantic similarity between pairs, classify relationships between pairs, rank relevant documents for queries, find translated sentence pairs, rerank documents according to instructions, assign multiple labels to each example, reorder candidate documents by relevance on MTEB Multilingual v2 · mean over tasks in 1037 languages including 'Auhelawa, Abau, Achi, Achinese, Achuar-Shiwiar, Adzera, Afrikaans, Agarabi; tasks receive equal weight
F2LLM v2 14B68.7
F2LLM v2 8B68.1
| Benchmark | F2LLM v2 14B | F2LLM v2 8B |
|---|---|---|
| MTEB multilingual v2 · Mean over tasks · multilingual (1037 languages) | 68.7 | 68.1 |
Specs
| Spec | F2LLM v2 14B | F2LLM v2 8B |
|---|---|---|
| Context | 41K | 41K |
| Weights | Open | Open |
| Released | Mar 2026 | Mar 2026 |
| Dimensions | 5,120 | 4,096 |
| Max input | 41K tokens | 41K tokens |
| Languages | en, es, Estonian +80 | en, es, Estonian +80 |
| Memory (4-bit) | 8.4 GB | 4.5 GB |
| Licence | Apache-2.0 | Apache-2.0 |
| Commercial use | Allowed | Allowed |
What breaks when you switch
F2LLM v2 14B → F2LLM v2 8B
Re-embed your whole corpus›
Vectors from different models can't be mixed; dimensions change from 5,120 to 4,096.
F2LLM v2 8B → F2LLM v2 14B
Re-embed your whole corpus›
Vectors from different models can't be mixed; dimensions change from 4,096 to 5,120.