Model reference · open weights

kosmos-2-patch14-224

kosmos-2-patch14-224 is an open-weight language model from microsoft, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

LLMs microsoft 1 variants 189k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What kosmos-2-patch14-224 is

Kosmos-2: Grounding Multimodal Large Language Models to the World This Hub repository contains a HuggingFace's transformers implementation of the original Kosmos-2 model from Microsoft. How to Get Started with the Model Use the code below to get started with the model. Tasks This model is capable of performing different tasks through changing the prompts. First, let's define a function to run a prompt. Here are the tasks Kosmos-2 could perform: Multimodal Grounding • Phrase Grounding • Referring Expression Comprehension Multimodal Referring • Referring expression generation Perception-Language Tasks • Grounded VQA • Grounded VQA with multimodal referring via bounding boxes Grounded Image captioning • Brief • Detailed Draw the bounding bboxes of the entities on the image Once you have the entities, you can use the following helper function to draw their bounding bboxes on the image: Here is the annotated image: BibTex and citation info

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

Makermicrosoft
TypeLanguage models
Parameters (lead)1.7B
Variants1
Runs withtransformers
Released2023-10-02
Popularity189k downloads / month
Likes183
LicenceOpen weights

How it works

How language models work

Your prompttext / messagesTransformerattention over tokensNext-token loopgenerate + streamResponsetext · tool callsA language model reads your tokens and predicts the next one, again and again, streaming the reply back.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
kosmos-2-patch14-2241.7BBF16~3.8 GBWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys kosmos-2-patch14-224 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (kosmos-2-patch14-224 below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"kosmos-2-patch14-224","messages":[{"role":"user","content":"Hello"}]}'

Details

Languages, data & research

Tags

transformers pytorch safetensors kosmos-2 image-text-to-text image-captioning image-to-text endpoints_compatible

Licence

Open weights

Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want kosmos-2-patch14-224 on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More language models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms