lm-kit/gemma-3-4b-instruct-gguf Q5_K_M 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
lm-kit/gemma-3-4b-instruct-gguf overview
Model Summary This repository hosts quantized versions of the Gemma 3 4B instruct model. Format: GGUF Converter: llama.cpp 7841fc723e059d1fd9640e5c0ef19050fcc7c698 Quantizer: LM-Kit.NET 2025.3.4 For more detailed information on the base model, please visit the following link
Downloads
820
Likes
1
Pipeline
—
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
11 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| gemma-3-it-4B-F16.gguf | GGUF | F16 | 7.23 GB | Download |
| gemma-3-it-4B-Q2_K.gguf | GGUF | Q2_K | 1.61 GB | Download |
| gemma-3-it-4B-Q3_K_L.gguf | GGUF | Q3_K_L | 2.08 GB | Download |
| gemma-3-it-4B-Q3_K_M.gguf | GGUF | Q3_K_M | 1.95 GB | Download |
| gemma-3-it-4B-Q3_K_S.gguf | GGUF | Q3_K_S | 1.80 GB | Download |
| gemma-3-it-4B-Q4_K_M.gguf | GGUF | Q4_K_M | 2.32 GB | Download |
| gemma-3-it-4B-Q4_K_S.gguf | GGUF | Q4_K_S | 2.21 GB | Download |
| gemma-3-it-4B-Q5_K_M.gguf | GGUF | Q5_K_M | 2.64 GB | Download |
| gemma-3-it-4B-Q5_K_S.gguf | GGUF | Q5_K_S | 2.57 GB | Download |
| gemma-3-it-4B-Q6_K.gguf | GGUF | Q6_K | 2.97 GB | Download |
| gemma-3-it-4B-Q8_0.gguf | GGUF | — | 3.85 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"license": "gemma",
"frontmatter": {
"license": "gemma"
},
"hero_image_url": "",
"summary": "## Model Summary This repository hosts quantized versions of the Gemma 3 4B instruct model. **Format:** GGUF **Converter:** llama.cpp 7841fc723e059d1fd9640e5c0ef19050fcc7c698 **Quantizer:** LM-Kit.NET 2025.3.4 For more detailed information on the base model, please visit the following link",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nlicense: gemma\n---\n## Model Summary\n\nThis repository hosts quantized versions of the Gemma 3 4B instruct model.\n\n**Format:** GGUF \n**Converter:** llama.cpp 7841fc723e059d1fd9640e5c0ef19050fcc7c698 \n**Quantizer:** LM-Kit.NET 2025.3.4\n\nFor more detailed information on the base model, please visit the following link\n\n- [Gemma-3-4b-it ](https://huggingface.co/google/gemma-3-4b-it)",
"related_quantizations": []
},
"tags": [
"gguf",
"license:gemma",
"endpoints_compatible",
"region:us",
"conversational"
],
"likes": 1,
"downloads": 820,
"gated": false,
"private": false,
"last_modified": "2025-03-12T10:42:54.000Z",
"created_at": "2025-03-12T09:22:00.000Z",
"pipeline_tag": "",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "67d15238d4979ccde6e81d5b",
"id": "lm-kit/gemma-3-4b-instruct-gguf",
"modelId": "lm-kit/gemma-3-4b-instruct-gguf",
"sha": "3ee9d9c4efb882fb411b4232cfc1d56045677af0",
"createdAt": "2025-03-12T09:22:00.000Z",
"lastModified": "2025-03-12T10:42:54.000Z",
"author": "lm-kit",
"downloads": 820,
"likes": 1,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "",
"siblings_count": 13
}