arabellako22
/

Chyon-Gemma-4

vision-language-model

not-recommended

Model card Files Files and versions

Chyon-Gemma-4 — Legacy GGUF Export

Status: not recommended for the current Chyon persona release. This is an earlier GGUF and multimodal-projector export retained for reproducibility.

Use the verified Chyon GGUF v2 release for the current AI 키온이 (Chyoni) model.

Files

gemma-4-e2b-it.Q4_K_M.gguf
gemma-4-e2b-it.F16-mmproj.gguf

Historical usage

# Text-only runtime
llama-cli -hf arabellako22/Chyon-Gemma-4 --jinja

# Multimodal runtime
llama-mtmd-cli -hf arabellako22/Chyon-Gemma-4 --jinja

Limitations

This repository does not contain the verification record used for the current Chyon v2 release.
Its relationship to the current persona adapter and verified 16-bit re-merge is not documented in the original card.
Ollama may not support separate multimodal projector files in this layout.

For the documented model lineage, use the Chyon LoRA adapter, verified full model, or verified GGUF v2 release.

Downloads last month: 47

GGUF

Model size

5B params

Architecture

gemma4

Hardware compatibility

Log In to add your hardware

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for arabellako22/Chyon-Gemma-4

Base model

google/gemma-4-E2B

Finetuned

google/gemma-4-E2B-it

Finetuned

unsloth/gemma-4-E2B-it

Quantized

(23)

this model