ModelListedExternal

Gemma 3 12b It GGUF

See our collection for all versions of Gemma 3 including GGUF, 4-bit & 16-bit formats.

Sourcehuggingface.co/unsloth/gemma-3-12b-it-GGUF

KindText modelBase modelgoogle/gemma-3-12b-itBgrade

Model source

Kind: Text model
File size: 815 MB–21.9 GB
Base model: google/gemma-3-12b-it
Updated: Oct 20, 2026
Source: Hugging Face

Source excerpt

See our collection for all versions of Gemma 3 including GGUF, 4-bit & 16-bit formats.

Sources

1 source

Hugging FacePrimary

huggingface.co/unsloth/gemma-3-12b-it-GGUF

Verified Oct 20

Model artifacts

24 artifacts

gemma-3-12b-it-BF16.gguf

gguf · bf16 · 21.9 GB · SHA-256 276920b11d80…82f2

gemma-3-12b-it-IQ4_NL.gguf

gguf · 6.41 GB · SHA-256 63db34d705d7…715f

gemma-3-12b-it-IQ4_XS.gguf

gguf · 6.10 GB · SHA-256 e209a303d9d0…8c65

gemma-3-12b-it-Q2_K_L.gguf

gguf · q2_k · 4.44 GB · SHA-256 e506f8ad03e4…8a9a

gemma-3-12b-it-Q3_K_M.gguf

gguf · q3_k · 5.60 GB · SHA-256 d8ab409bfc66…a885

gemma-3-12b-it-Q3_K_S.gguf

gguf · q3_k · 5.08 GB · SHA-256 99d72d010140…d440

gemma-3-12b-it-Q4_0.gguf

gguf · q4_0 · 6.43 GB · SHA-256 80acb48f341b…f5eb

gemma-3-12b-it-Q4_1.gguf

gguf · q4_1 · 7.04 GB · SHA-256 30fb75827371…ac8e

gemma-3-12b-it-Q4_K_M.gguf

gguf · q4_k · 6.80 GB · SHA-256 15b8fd9d8672…b3ff

gemma-3-12b-it-Q5_K_M.gguf

gguf · q5_k · 7.87 GB · SHA-256 ea6d227c4983…08b3

gemma-3-12b-it-UD-IQ1_M.gguf

gguf · 3.03 GB · SHA-256 285c6d06c441…37ef

gemma-3-12b-it-UD-IQ1_S.gguf

gguf · 2.85 GB · SHA-256 0ec1302aeb6c…1c77

gemma-3-12b-it-UD-IQ2_M.gguf

gguf · 4.07 GB · SHA-256 5c9e8c2a2cd7…1d77

gemma-3-12b-it-UD-IQ2_XXS.gguf

gguf · 3.36 GB · SHA-256 1aafbfdeef6a…2e8d

gemma-3-12b-it-UD-IQ3_XXS.gguf

gguf · 4.50 GB · SHA-256 eddc5fdf75bc…80c5

gemma-3-12b-it-UD-Q2_K_XL.gguf

gguf · q2_k · 4.53 GB · SHA-256 85e9f7e21c0e…e980

gemma-3-12b-it-UD-Q3_K_XL.gguf

gguf · q3_k · 5.72 GB · SHA-256 51b181d0c4b3…357b

gemma-3-12b-it-UD-Q4_K_XL.gguf

gguf · q4_k · 6.92 GB · SHA-256 68d0b2d09575…b0b3

gemma-3-12b-it-UD-Q5_K_XL.gguf

gguf · q5_k · 7.88 GB · SHA-256 02d547d3cb4b…bace

gemma-3-12b-it-UD-Q6_K_XL.gguf

gguf · q6_k · 9.83 GB · SHA-256 6b8d4ec90c93…70e9

gemma-3-12b-it-UD-Q8_K_XL.gguf

gguf · q8_k · 13.4 GB · SHA-256 fedf9f286e58…a8a0

mmproj-BF16.gguf

gguf · bf16 · 815 MB · SHA-256 a3f12a897e95…22f9

mmproj-F16.gguf

gguf · 815 MB · SHA-256 5de4ccfc379f…4f71

mmproj-F32.gguf

gguf · 1.56 GB · SHA-256 9abd89fef71f…66ce

Source excerpts

3 excerpts

ReadmeAug 4huggingface.co/unsloth/gemma-3-12b-it-GGUF

--- base_model: google/gemma-3-12b-it language: - en library_name: transformers license: gemma tags: - unsloth - transformers - gemma3 - gemma - google --- <div> <p style="margin-bottom: 0; margin-top: 0;"> <strong>See <a href="https://huggingface.co/collections/unsloth/gemma-3-67d12b7e8816ec6efa7e4e5b">our collection</a> for all versions of Gemma 3 including GGUF, 4-bit & 16-bit formats.</strong> </p> <p style="margin-bottom: 0;"> <em><a href="https://docs.unsloth.ai/basics/tutorial-how-to-run-gemma-3-effectively">Read our Guide</a> to see how to Run Gemma 3 correctly.</em> </p> <div style="display: flex; gap: 5px; align-items: center; "> <a href="https://github.com/unslothai/unsloth/"> <img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133"> </a> <a href="https://discord.gg/unsloth"> <img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173"> </a> <a href="https://docs.unsloth.ai/basics/tutorial-how-to-run-deepseek-r1-on-your-own-local-device"> <img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143"> </a> </div> <h1 style="margin-top: 0rem;">✨ Fine-tune Gemma 3 with Unsloth!</h1> </div> - Fine-tune Gemma 3 (12B) for free using our Google [Colab notebook here](https://docs.unsloth.ai/get-started/unsloth-notebooks)! - Read our Blog about Gemma 3 support: [unsloth.ai/blog/gemma3](https://unsloth.ai/blog/gemma3) - View the rest of our notebooks in our [docs here](https://docs.unsloth.ai/get-started/unsloth-notebooks). - Export your fine-tuned model to GGUF, Ollama, llama.cpp or 🤗HF. | Unsloth supports | Free Notebooks | Performance | Memory use | |-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------| | **GRPO with Gemma 3 (12B)** | [▶️ Start on Colab](https://docs.unsloth.ai/get-started/unsloth-notebooks) | 2x faster | 80% less | | **Llama-3.2 (3B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(1B_and_3B)-Conversational.ipynb) | 2.4x faster | 58% less | | **Llama-3.2 (11B vision)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(11B)-Vision.ipynb) | 2x...

NoteOct 20huggingface.co/unsloth/gemma-3-12b-it-GGUF

Source context: 65120 downloads · 202 likes · Pipeline image-text-to-text · Library transformers · Repo unsloth/gemma-3-12b-it-GGUF

NoteAug 4huggingface.co/unsloth/gemma-3-12b-it-GGUF

Source context: 73024 downloads · 192 likes · Pipeline image-text-to-text · Library transformers · Repo unsloth/gemma-3-12b-it-GGUF