LLM EU
Menu
Models

GLM 4.6V Flash

Z.ai (Zhipu AI)

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

It accepts text and images and answers in text. GLM 4.6V Flash is an open-weight vision-language model from Z.ai (Zhipu AI) with 10.3B parameters, published under MIT. The published configuration records no context window, so this card carries none. The repository was created in December 2025 and is mirrored on Hugging Face. It is a base checkpoint without instruction tuning. The card is catalogue-only: LLM EU does not run this model. The publisher lists 2 languages, 1 of them among the languages the European Union publishes in.

Specifications

Provider
Z.ai (Zhipu AI) (CN)
Context window
Not verified: the provider has not documented this claim.
Parameters
10.3B
Modalities
text, vision
License
mit · licence
Open weights
yes
Release date
07 Dec 2025
Tasks
Vision, Low cost

Languages

Strong: en

Adequate: zh

Strong

  • en

Adequate

  • zh

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 10.3B parameters it fits on a single accelerator
  • the model page lists en

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 10.3B parameters, self-hosting needs a single accelerator with enough memory for the weights
  • vision checkpoints are heavier to serve than their parameter count alone suggests, because the image encoder and pre-processing run alongside the language model