GraySoft
Projects Models About FAQ Contact Download guIDE →

lovedheart/qwen3-next-reap-30b-a3b-instruct-gguf Q2_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-30b-a3b-instruct-gguf overview

!qwen3-next-instruction Qwen3-Next-REAP-30B-A3B-Instruct has the following specifications: Number of Linear Attention Heads: 32 for V and 16 for QK Head Dimension: 128

gguftext-generation-inferencebase_model:Qwen/Qwen3-Next-80B-A3B-Instructbase_model:quantized:Qwen/Qwen3-Next-80B-A3B-Instructlicense:apache-2.0endpoints_compatibleregion:usconversational
lovedheart/qwen3-next-reap-30b-a3b-instruct-gguf visual
Downloads
177
Likes
3
Pipeline
Library
Visibility
Public
Access
Open

Repository Files & Downloads

11 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
Qwen3-Next-30B-A3B-Instruct-BF16-00001-of-00004.gguf GGUF BF16 18.53 GB Download
Qwen3-Next-30B-A3B-Instruct-BF16-00002-of-00004.gguf GGUF BF16 18.27 GB Download
Qwen3-Next-30B-A3B-Instruct-BF16-00003-of-00004.gguf GGUF BF16 18.25 GB Download
Qwen3-Next-30B-A3B-Instruct-BF16-00004-of-00004.gguf GGUF BF16 3.34 GB Download
Qwen3-Next-REAP-30B-A3B-Instruct-Q2_K_S.gguf GGUF Q2_K_S 12.50 GB Download
Qwen3-Next-REAP-30B-A3B-Instruct-Q2_K_XL.gguf GGUF Q2_K_XL 14.49 GB Download
Qwen3-Next-REAP-30B-A3B-Instruct-Q3_K_S.gguf GGUF Q3_K_S 15.57 GB Download
Qwen3-Next-REAP-30B-A3B-Instruct-Q4_K_XL.gguf GGUF Q4_K_XL 20.83 GB Download
Qwen3-Next-REAP-30B-A3B-Instruct-Q5_K_XL.gguf GGUF Q5_K_XL 23.60 GB Download
Qwen3-Next-REAP-30B-A3B-Instruct-Q6_K_XL.gguf GGUF Q6_K_XL 26.80 GB Download
Qwen3-Next-REAP-30B-A3B-Instruct-Q8_0.gguf GGUF 33.25 GB Download

Model Details Live

Model Slug
lovedheart/qwen3-next-reap-30b-a3b-instruct-gguf
Author
lovedheart
Pipeline Task
Library
Created
2026-02-02
Last Modified
2026-02-03
Gated
No
Private
No
HF SHA
7c78f23a44a98d5833351cef7cac3151cfc02ac6
License
apache-2.0
Language
Unknown
Base Model
Qwen/Qwen3-Next-80B-A3B-Instruct

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "base_model": [
      "Qwen/Qwen3-Next-80B-A3B-Instruct"
    ],
    "tags": [
      "text-generation-inference"
    ],
    "license": "apache-2.0",
    "frontmatter": {
      "base_model": [
        "Qwen/Qwen3-Next-80B-A3B-Instruct"
      ],
      "tags": [
        "text-generation-inference"
      ],
      "license": "apache-2.0"
    },
    "hero_image_url": "https://cdn-uploads.huggingface.co/production/uploads/68121d80da035a609e569a81/Ft9cmZlll_PehtFYkESxH.png",
    "summary": "!qwen3-next-instruction **Qwen3-Next-REAP-30B-A3B-Instruct** 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-Instruct\ntags:\n- text-generation-inference\nlicense: apache-2.0\n---\n\n\n\n![qwen3-next-instruction](https://cdn-uploads.huggingface.co/production/uploads/68121d80da035a609e569a81/Ft9cmZlll_PehtFYkESxH.png)\n\n**Qwen3-Next-REAP-30B-A3B-Instruct** has the following specifications:\n\n- **Type:** Causal Language Models\n- **Number of Parameters**: 30B 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: 192 (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**: 62.5% expert pruning",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "text-generation-inference",
    "base_model:Qwen/Qwen3-Next-80B-A3B-Instruct",
    "base_model:quantized:Qwen/Qwen3-Next-80B-A3B-Instruct",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 3,
  "downloads": 177,
  "gated": false,
  "private": false,
  "last_modified": "2026-02-03T16:41:02.000Z",
  "created_at": "2026-02-02T22:38:58.000Z",
  "pipeline_tag": "",
  "library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "698127823c70281a3ae1990d",
  "id": "lovedheart/Qwen3-Next-REAP-30B-A3B-Instruct-GGUF",
  "modelId": "lovedheart/Qwen3-Next-REAP-30B-A3B-Instruct-GGUF",
  "sha": "7c78f23a44a98d5833351cef7cac3151cfc02ac6",
  "createdAt": "2026-02-02T22:38:58.000Z",
  "lastModified": "2026-02-03T16:41:02.000Z",
  "author": "lovedheart",
  "downloads": 177,
  "likes": 3,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 13
}