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

gwejgteheg/gemma-4-12B-IT-QAT-Q4_K_M-DeepSeek-distill-GGUF overview

gemma 4 12B IT QAT Q4 K M DeepSeek distill GGUF : GGUF This model was finetuned and converted to GGUF format using Unsloth https://github.com/unslothai/unsloth…

ggufgemma4_unifiedllama.cppunslothvision-language-modelendpoints_compatibleregion:usconversational

Runs locally from ~167.0 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
1
Pipeline

Repository Files & Downloads

2 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
gemma-4-12B-it-qat-q4_0-unquantized.BF16-mmproj.ggufGGUFQ4_0167.0 MBDownload
gemma-4-12B-it-qat-q4_0-unquantized.Q4_K_M.ggufGGUFQ4_06.87 GBDownload

Model Details

Model IDgwejgteheg/gemma-4-12B-IT-QAT-Q4_K_M-DeepSeek-distill-GGUF
Authorgwejgteheg
Pipeline
License
Base model
Last modified2026-07-07T19:31:37.000Z

Model README

---

tags:

  • gguf
  • llama.cpp
  • unsloth
  • vision-language-model

---

gemma-4-12B-IT-QAT-Q4_K_M-DeepSeek-distill-GGUF : GGUF

This model was finetuned and converted to GGUF format using Unsloth.

Example usage:

  • For text only LLMs: llama-cli -hf gwejgteheg/gemma-4-12B-IT-QAT-Q4_K_M-DeepSeek-distill-GGUF --jinja
  • For multimodal models: llama-mtmd-cli -hf gwejgteheg/gemma-4-12B-IT-QAT-Q4_K_M-DeepSeek-distill-GGUF --jinja

Available Model files:

  • gemma-4-12B-it-qat-q4_0-unquantized.Q4_K_M.gguf
  • gemma-4-12B-it-qat-q4_0-unquantized.BF16-mmproj.gguf

This was trained 2x faster with Unsloth

<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>

Run gwejgteheg/gemma-4-12B-IT-QAT-Q4_K_M-DeepSeek-distill-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