GraySoft
Projects Models About FAQ Contact Download guIDE →

ggml-org/gemma-3n-e2b-it-gguf F16 GGUF - Free GGUF Download is indexed on GraySoft with repository links, GGUF quant files, and Hugging Face metadata. This page helps you pick a local model for guIDE or other runtimes. See related models in the same shard below.

Model Intelligence Sheet

ggml-org/gemma-3n-e2b-it-gguf overview

Original model: https://huggingface.co/google/gemma-3n-E2B-it Model Page: Gemma 3n Resources and Technical Documentation: Terms of Use: Terms\ Authors: Google DeepMind

ggufbase_model:google/gemma-3n-E2B-itbase_model:quantized:google/gemma-3n-E2B-itlicense:gemmaendpoints_compatibleregion:usconversational
ggml-org/gemma-3n-e2b-it-gguf visual
Downloads
5,111
Likes
24
Pipeline
Library
gguf
Visibility
Public
Access
Open

Repository Files & Downloads

2 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
gemma-3n-E2B-it-Q8_0.gguf GGUF 4.46 GB Download
gemma-3n-E2B-it-f16.gguf GGUF F16 8.31 GB Download

Model Details Live

Model Slug
ggml-org/gemma-3n-e2b-it-gguf
Author
ggml-org
Pipeline Task
Library
gguf
Created
2025-06-26
Last Modified
2025-08-22
Gated
No
Private
No
HF SHA
989cffaba23976934324f5e3abfabe31b30eb73b
License
gemma
Language
Unknown
Base Model
google/gemma-3n-E2B-it

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "license": "gemma",
    "library_name": "gguf",
    "base_model": "google/gemma-3n-E2B-it",
    "frontmatter": {
      "license": "gemma",
      "library_name": "gguf",
      "base_model": "google/gemma-3n-E2B-it"
    },
    "hero_image_url": "",
    "summary": "**Original model**: https://huggingface.co/google/gemma-3n-E2B-it **Model Page**: Gemma 3n **Resources and Technical Documentation**: **Terms of Use**: Terms\\ **Authors**: Google DeepMind",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: gemma\nlibrary_name: gguf\nbase_model: google/gemma-3n-E2B-it\n---\n\n> [!Note]\n> This version does not contain multimodal support. We are still working on adding multimodal.\n\n# Gemma 3n model card\n\n**Original model**: https://huggingface.co/google/gemma-3n-E2B-it\n\n**Model Page**: [Gemma 3n](https://ai.google.dev/gemma/docs/gemma-3n)\n\n**Resources and Technical Documentation**:\n\n-   [Responsible Generative AI Toolkit](https://ai.google.dev/responsible)\n-   [Gemma on Kaggle](https://www.kaggle.com/models/google/gemma-3n)\n-   [Gemma on HuggingFace](https://huggingface.co/collections/google/gemma-3n-685065323f5984ef315c93f4)\n-   [Gemma on Vertex Model Garden](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/gemma3n)\n\n**Terms of Use**: [Terms](https://ai.google.dev/gemma/terms)\\\n**Authors**: Google DeepMind\n\n## Example usage\n\n### With llama.cpp\n\nTo install llama.cpp on your system, see [installation guide](https://github.com/ggml-org/llama.cpp/blob/master/README.md)\n\n```sh\nllama-cli -hf ggml-org/gemma-3n-E2B-it-GGUF:Q8_0 -fa -c 0 --jinja\n```\n\n### With LM Studio\n\nSearch for `gemma-3n-E2B-it-GGUF` and add it to your model library",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "base_model:google/gemma-3n-E2B-it",
    "base_model:quantized:google/gemma-3n-E2B-it",
    "license:gemma",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 24,
  "downloads": 5111,
  "gated": false,
  "private": false,
  "last_modified": "2025-08-22T11:03:00.000Z",
  "created_at": "2025-06-26T10:09:32.000Z",
  "pipeline_tag": "",
  "library_name": "gguf"
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "685d1c5c8b688d7f3e4fe03a",
  "id": "ggml-org/gemma-3n-E2B-it-GGUF",
  "modelId": "ggml-org/gemma-3n-E2B-it-GGUF",
  "sha": "989cffaba23976934324f5e3abfabe31b30eb73b",
  "createdAt": "2025-06-26T10:09:32.000Z",
  "lastModified": "2025-08-22T11:03:00.000Z",
  "author": "ggml-org",
  "downloads": 5111,
  "likes": 24,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "gguf",
  "siblings_count": 4
}