Qabbel
Phi 3.5 Vision Instruct vs Phi-4-multimodal-instruct
Qiegħed żewġ mudelli sa erbgħa ma' xulxin fuq l-oqsma li jiddeċiedu deployment: kuntest, prezz, reġjun, liċenzja, lingwi, hosting, u x'hu verifikat.
| Phi 3.5 Vision Instruct | Phi-4-multimodal-instruct | |
|---|---|---|
| Fornitur | Microsoft | Microsoft |
| Parametri | 4.1B | 5.57B |
| Tieqa tal-kuntest | Mhux verifikat: il-fornitur ma ddokumentax din id-dikjarazzjoni. | 131k |
| Liċenzja | mit | mit |
| Modalitajiet | text, vision | text, vision, audio |
| Data tar-rilaxx | 16 Aww 2024 | 24 Fra 2025 |
| Lingwi | Qawwi: — Adekwat: nlp | Qawwi: en, de, fr, es, it, pt Adekwat: nl, pl, sv, da, fi, cs, ru, uk, ar, zh, ja, ko, hi, tr |
| Piżijiet miftuħa | iva | iva |
| Kompiti | Viżjoni, Sommarizzazzjoni | Viżjoni, Sommarizzazzjoni, Appoġġ multilingwi, Spiża baxxa |
Fejn żewġ mudelli jvarjaw, din it-tabella turi d-differenza u tieqaf. LLM EU ma tippubblikax badge ta' rebbieħ mingħajr punteġġ dokumentat għal dik il-kompitu, u figura nieqsa tibqa' nieqsa minflok ma ssir żero.
Meta tużah
Phi 3.5 Vision Instruct
Saħħiet
- 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 4.1B parameters it fits on a single accelerator
- instruction-tuned checkpoint with a chat template in the repository
Limiti
- catalogue only — 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 4.1B parameters, the weights fit on a single modest accelerator
- vision checkpoints are heavier to serve than their parameter count alone suggests, because the image encoder and pre-processing run alongside the language model
Kompiti
Phi-4-multimodal-instruct
Saħħiet
- text, image and speech input at 5.6B parameters
- 128K-token context for document batches
- MIT licence
- 23 declared languages including most large EU languages
Limiti
- modality-specific quality is below dedicated single-modality models
- English-centric training data
- no evaluation has been run by LLM EU
Kompiti
Kompiti: Viżjoni, Sommarizzazzjoni