lovedheart/qwen3-next-reap-20b-a3b-thinking-gguf Q6_K_XL 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
lovedheart/qwen3-next-reap-20b-a3b-thinking-gguf overview
!qwen3-next-thinking Qwen3-Next-REAP-20B-A3B-Thinking has the following specifications: Number of Linear Attention Heads: 32 for V and 16 for QK Head Dimension: 128
Downloads
224
Likes
3
Pipeline
—
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
9 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Qwen3-Next-REAP-20B-A3B-Thinking-BF16.gguf | GGUF | BF16 | 40.37 GB | Download |
| Qwen3-Next-REAP-20B-A3B-Thinking-IQ1_M.gguf | GGUF | IQ1_M | 9.00 GB | Download |
| Qwen3-Next-REAP-20B-A3B-Thinking-Q2_K_XL.gguf | GGUF | Q2_K_XL | 11.15 GB | Download |
| Qwen3-Next-REAP-20B-A3B-Thinking-Q3_K_XL.gguf | GGUF | Q3_K_XL | 11.15 GB | Download |
| Qwen3-Next-REAP-20B-A3B-Thinking-Q4_K_XL.gguf | GGUF | Q4_K_XL | 15.41 GB | Download |
| Qwen3-Next-REAP-20B-A3B-Thinking-Q4_K_XXL.gguf | GGUF | Q4_K_XXL | 15.60 GB | Download |
| Qwen3-Next-REAP-20B-A3B-Thinking-Q5_K_XL.gguf | GGUF | Q5_K_XL | 17.29 GB | Download |
| Qwen3-Next-REAP-20B-A3B-Thinking-Q6_K_XL.gguf | GGUF | Q6_K_XL | 19.28 GB | Download |
| Qwen3-Next-REAP-20B-A3B-Thinking-imatrix.gguf | GGUF | — | 111.63 MB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"base_model": [
"Qwen/Qwen3-Next-80B-A3B-Thinking"
],
"tags": [
"text-generation-inference"
],
"license": "apache-2.0",
"frontmatter": {
"base_model": [
"Qwen/Qwen3-Next-80B-A3B-Thinking"
],
"tags": [
"text-generation-inference"
],
"license": "apache-2.0"
},
"hero_image_url": "https://cdn-uploads.huggingface.co/production/uploads/68121d80da035a609e569a81/tXHS7ClRRpoA4sZ2qPegd.png",
"summary": "!qwen3-next-thinking **Qwen3-Next-REAP-20B-A3B-Thinking** has the following specifications: **Number of Linear Attention Heads: 32 for V and 16 for QK **Head Dimension: 128",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nbase_model:\n- Qwen/Qwen3-Next-80B-A3B-Thinking\ntags:\n- text-generation-inference\nlicense: apache-2.0\n---\n\n\n\n\n\n\n**Qwen3-Next-REAP-20B-A3B-Thinking** has the following specifications:\n\n- **Type:** Causal Language Models\n- **Number of Parameters**: 20B in total and 3B activated\n- **Hidden Dimension**: 2048\n- **Number of Layers**: 48\n- **Hybrid Layout**: 12 * (3 * (Gated DeltaNet -> MoE) -> 1 * (Gated Attention -> MoE))\n- **Gated Attention**:\n- **Number of Attention Heads**: 16 for Q and 2 for KV\n- **Head Dimension**: 256\n- **Rotary Position Embedding Dimension**: 64\n- **Gated DeltaNet**: \n **Number of Linear Attention Heads: 32 for V and 16 for QK \n **Head Dimension: 128\n- **Mixture of Experts**:\n- **Number of Experts: 128 (uniformly pruned from 512)\n- **Number of Activated Experts: 10\n- **Number of Shared Experts: 1\n- **Context Length**: 262,144 natively and extensible up to 1,010,000 tokens\n- **Compression Method**: REAP (Router-weighted Expert Activation Pruning)\n- **Compression Ratio**: 75% expert pruning\n- **Specialized**: Math, Physics, Control Engineering, Scientific Writing",
"related_quantizations": []
},
"tags": [
"gguf",
"text-generation-inference",
"base_model:Qwen/Qwen3-Next-80B-A3B-Thinking",
"base_model:quantized:Qwen/Qwen3-Next-80B-A3B-Thinking",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
],
"likes": 3,
"downloads": 224,
"gated": false,
"private": false,
"last_modified": "2026-01-27T11:22:46.000Z",
"created_at": "2026-01-18T23:06:41.000Z",
"pipeline_tag": "",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "696d6781d7b41b1cf65d7185",
"id": "lovedheart/Qwen3-Next-REAP-20B-A3B-Thinking-GGUF",
"modelId": "lovedheart/Qwen3-Next-REAP-20B-A3B-Thinking-GGUF",
"sha": "398927f5c32abbacbe37fd5e4a8b0ade279f68a2",
"createdAt": "2026-01-18T23:06:41.000Z",
"lastModified": "2026-01-27T11:22:46.000Z",
"author": "lovedheart",
"downloads": 224,
"likes": 3,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "",
"siblings_count": 11
}