GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

arabellako22/chyon_gemma_4_gguf overview

Chyon Gemma 4 GGUF This is a merged and quantized GGUF version of the LoRA fine tuned model. Source Base model: unsloth/gemma 4 E2B it LoRA adapter: arabellako…

llama.cppggufgemmaconversationalkoreanqlorabase_model:unsloth/gemma-4-E2B-itbase_model:quantized:unsloth/gemma-4-E2B-itlicense:apache-2.0endpoints_compatibleregion:us

Runs locally from ~3.19 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline

Repository Files & Downloads

2 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
chyon-gemma-4.Q4_K_M.ggufGGUFGGUF3.19 GBDownload
chyon-gemma-4.Q5_K_M.ggufGGUFGGUF3.38 GBDownload

Model Details

Model IDarabellako22/chyon_gemma_4_gguf
Authorarabellako22
Pipeline
Licenseapache-2.0
Base modelunsloth/gemma-4-E2B-it
Last modified2026-06-20T04:22:40.000Z

Model README

---

license: apache-2.0

base_model: unsloth/gemma-4-E2B-it

library_name: llama.cpp

tags:

  • gguf
  • gemma
  • conversational
  • korean
  • qlora

---

Chyon-Gemma-4 GGUF

This is a merged and quantized GGUF version of the LoRA fine-tuned model.

Source

  • Base model: unsloth/gemma-4-E2B-it
  • LoRA adapter: arabellako22/chyon_lora_model
  • Merged full model: arabellako22/chyon_merged_full_gemma_4

Files

  • chyon-gemma-4.Q4_K_M.gguf: recommended local version
  • chyon-gemma-4.Q5_K_M.gguf: better quality, larger size

Recommended prompt template

Use the same Gemma-style template used during training:

<start_of_turn>user
{{ system_prompt }}

{{ user_prompt }}<end_of_turn>
<start_of_turn>model

Run arabellako22/chyon_gemma_4_gguf with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models