abiray/gemma-4-31b-claude-4.6-opus-reasoning-distilled-gguf Q6_K 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
abiray/gemma-4-31b-claude-4.6-opus-reasoning-distilled-gguf overview
This repository contains GGUF format model files for EganAI/gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled.
Downloads
5,630
Likes
7
Pipeline
text-generation
Library
llama-cpp
Visibility
Public
Access
Open
Repository Files & Downloads
5 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled-Q3_K_M.gguf | GGUF | Q3_K_M | 14.24 GB | Download |
| gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled-Q4_K_M.gguf | GGUF | Q4_K_M | 17.40 GB | Download |
| gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled-Q5_K_M.gguf | GGUF | Q5_K_M | 20.35 GB | Download |
| gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled-Q6_K.gguf | GGUF | Q6_K | 23.47 GB | Download |
| gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled-Q8_0.gguf | GGUF | — | 30.39 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"base_model": "EganAI/gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled",
"library_name": "llama-cpp",
"tags": [
"gemma4",
"gemma",
"reasoning",
"claude-opus",
"distillation",
"gguf",
"quantized"
],
"pipeline_tag": "text-generation",
"frontmatter": {
"base_model": "EganAI/gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled",
"library_name": "llama-cpp",
"tags": [
"gemma4",
"gemma",
"reasoning",
"claude-opus",
"distillation",
"gguf",
"quantized"
],
"pipeline_tag": "text-generation"
},
"hero_image_url": "",
"summary": "This repository contains GGUF format model files for EganAI/gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled.",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nbase_model: EganAI/gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled\nlibrary_name: llama-cpp\ntags:\n- gemma4\n- gemma\n- reasoning\n- claude-opus\n- distillation\n- gguf\n- quantized\npipeline_tag: text-generation\n---\n\n# gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled-GGUF\n\nThis repository contains GGUF format model files for [EganAI/gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled](https://huggingface.co/EganAI/gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled). \n\n## Model Details\n* **Base Architecture:** Gemma 4 (31B parameters)\n* **Training Focus:** Full parameter SFT on 12,680 Claude Opus 4.6 reasoning traces.\n\n## Available Quantizations\n\n| File | Size |\n| :--- | :--- |\n| `gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled-Q3_K_M.gguf` | 15.3 GB |\n| `gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled-Q4_K_M.gguf` | 18.7 GB |\n| `gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled-Q5_K_M.gguf` | 21.8 GB |\n| `gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled-Q6_K.gguf` | 25.2 GB |\n| `gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled-Q8_0.gguf` | 32.6 GB |\n\n**Recommendation:** `Q4_K_M` provides the optimal balance between inference speed, memory consumption, and preserving the model's reasoning accuracy.\n\n## Stop Sequence\nTo ensure generation stops cleanly, configure your inference engine or UI to use the following stop sequence (native to the Gemma 4 template):\n* `<end_of_turn>`\n\n## Usage Instructions\n\n### Using `llama.cpp` CLI\n```bash\n./llama-cli -m gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled-Q4_K_M.gguf -p \"Prove that the square root of 2 is irrational.\" -n 1024",
"related_quantizations": []
},
"tags": [
"llama-cpp",
"gguf",
"gemma4",
"gemma",
"reasoning",
"claude-opus",
"distillation",
"quantized",
"text-generation",
"base_model:EganAI/gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled",
"base_model:quantized:EganAI/gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled",
"endpoints_compatible",
"region:us",
"conversational"
],
"likes": 7,
"downloads": 5630,
"gated": false,
"private": false,
"last_modified": "2026-04-06T15:25:24.000Z",
"created_at": "2026-04-06T14:55:13.000Z",
"pipeline_tag": "text-generation",
"library_name": "llama-cpp"
}
Source payload excerpt (from Hugging Face API)
{
"_id": "69d3c951a11c8adeff8084f9",
"id": "Abiray/gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled-GGUF",
"modelId": "Abiray/gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled-GGUF",
"sha": "ac6076dcb1996d1747cafffe07c92fd31d230b56",
"createdAt": "2026-04-06T14:55:13.000Z",
"lastModified": "2026-04-06T15:25:24.000Z",
"author": "Abiray",
"downloads": 5630,
"likes": 7,
"gated": false,
"private": false,
"pipeline_tag": "text-generation",
"library_name": "llama-cpp",
"siblings_count": 7
}