Title: Phi 2 vs Phi-4: Parametre, Licens, Kontekstvindue %E2%80%94 LLM EU
Canonical: https://llmeu.com/da/compare/phi-2-vs-phi-4/
Markdown mirror: https://llmeu.com/da/compare/phi-2-vs-phi-4.md
Machine-readable: https://llmeu.com/llms.txt (index) - https://llmeu.com/llms-full.txt (full catalogue) - https://llmeu.com/llms-catalogue.json

# Phi 2 vs Phi-4

S%C3%A6t to til fire modeller side om side p%C3%A5 de felter, der afg%C3%B8r en udrulning: kontekst, pris, region, licens, sprog, hosting og hvad der er verificeret.

Hvor to modeller adskiller sig, viser denne tabel forskellen og stopper. LLM EU offentligg%C3%B8r ikke et vinderbadge uden en dokumenteret score for den opgave, og et manglende tal forbliver manglende i stedet for at blive et nul.

## Hvorn%C3%A5r man bruger den

### [Phi 2](/da/models/phi-2/)

#### Styrker

- open weights are published on Hugging Face and can be downloaded without a vendor agreement
- mit licence, so commercial self-hosting is permitted without a separate agreement
- at 2.8B parameters it fits on a single accelerator
- the model page lists en

#### Begr%C3%A6nsninger

- catalogue only %E2%80%94 LLM EU does not run this model, and nothing on this card implies an LLM EU endpoint
- no evaluation has been run by LLM EU
- the published configuration records no context window, so the card carries none
- at 2.8B parameters, the weights fit on a single modest accelerator

#### Opgaver

[R%C3%A6sonnement](/da/tasks/reasoning/), [Lav pris](/da/tasks/cheap/)

### [Phi-4](/da/models/phi-4/)

#### Styrker

- strong MMLU and maths scores at 14B parameters
- MIT licence without user thresholds
- fits a single 40GB accelerator at BF16

#### Begr%C3%A6nsninger

- 16K-token context window
- declared English-only; EU-language performance is not documented
- training leans on synthetic data, which narrows domain robustness

#### Opgaver

[R%C3%A6sonnement](/da/tasks/reasoning/), [Resum%C3%A9](/da/tasks/summarization/), [Lav pris](/da/tasks/cheap/), [Genfinding (RAG)](/da/tasks/rag/)

**Opgaver:** [R%C3%A6sonnement](/da/tasks/reasoning/), [Lav pris](/da/tasks/cheap/)

## Sammenlign modeller

- [Aya 23 8B vs Phi-4](/da/compare/aya-23-8b-vs-phi-4/)
- [Aya Expanse 8B vs Phi-4](/da/compare/aya-expanse-8b-vs-phi-4/)
- [Blip2 Opt 2.7B vs Phi 2](/da/compare/blip2-opt-2-7b-vs-phi-2/)
- [NVIDIA Cosmos Reason2 2B vs Phi 2](/da/compare/cosmos-reason2-2b-vs-phi-2/)
- [DeepSeek Coder V2 Lite Instruct vs Phi-4](/da/compare/deepseek-coder-v2-lite-instruct-vs-phi-4/)
- [DeepSeek OCR vs Phi 2](/da/compare/deepseek-ocr-vs-phi-2/)