Models

Phi 3 Mini 4K Instruct

Microsoft

Catalogue only Open weights

Last reviewed:

Sovereignty and hosting

Catalogue only

This model is catalogued for reference. It is not hosted on LLM EU yet, and no first-party endpoint serves it here. Requests to it go to the provider directly, under that provider's own terms.

Summary

The checkpoint is instruction-tuned and ships a chat template. Phi 3 Mini 4K Instruct is published by Microsoft as open weights with 3.8B parameters under MIT. It takes text and returns text. The published configuration records no context window, so this card carries none. The repository was created in April 2024 and is mirrored on Hugging Face. The card is catalogue-only: LLM EU does not run this model. The publisher lists 3 languages, 2 of them among the languages the European Union publishes in.

Specifications

Provider
Microsoft (US)
Context window
Not verified: the provider has not documented this claim.
Parameters
3.8B
Modalities
text
License
mit · licence
Open weights
yes
Release date
22 Apr 2024
Tasks
Reasoning, Low cost, Summarisation

Languages

Strong: en, fr

Adequate: nlp

Strong

  • en
  • fr

Adequate

  • nlp

Not verified: the provider has not documented this claim. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.

When to use it

Strengths

  • 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 3.8B parameters it fits on a single accelerator
  • the model page lists en, fr
  • instruction-tuned checkpoint with a chat template in the repository

Limits

  • 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 3.8B parameters, the weights fit on a single modest accelerator