GraySoft
Projects Models About FAQ Contact Download guIDE →

mobilint/exaone-3.5-2.4b-instruct-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

mobilint/exaone-3.5-2.4b-instruct-gguf overview

This repository provides EXAONE 3.5 2.4B Instruct compiled and optimized for Mobilint NPU hardware, packaged for use with llama.cpp-mblt.

llama-cppggufmobilint-exaonemobilintexaonenputext-generationbase_model:LGAI-EXAONE/EXAONE-3.5-2.4B-Instructbase_model:quantized:LGAI-EXAONE/EXAONE-3.5-2.4B-Instructlicense:otherendpoints_compatibleregion:usconversational
mobilint/exaone-3.5-2.4b-instruct-gguf visual
Downloads
611
Likes
0
Pipeline
text-generation
Library
llama-cpp
Visibility
Public
Access
Open

Repository Files & Downloads

1 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
exaone-3.5-2.4b-instruct-vocab.gguf GGUF 3.99 MB Download

Model Details Live

Model Slug
mobilint/exaone-3.5-2.4b-instruct-gguf
Author
mobilint
Pipeline Task
text-generation
Library
llama-cpp
Created
2026-03-26
Last Modified
2026-04-08
Gated
No
Private
No
HF SHA
d80d2cec78250079b60c4e154270c1943b4fb838
License
other
Language
Unknown
Base Model
LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "license": "other",
    "license_name": "exaone",
    "license_link": "https://huggingface.co/LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct/blob/main/LICENSE",
    "pipeline_tag": "text-generation",
    "base_model": [
      "LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct"
    ],
    "base_model_relation": "quantized",
    "tags": [
      "mobilint",
      "exaone",
      "llama-cpp",
      "gguf",
      "npu"
    ],
    "library_name": "llama-cpp",
    "frontmatter": {
      "license": "other",
      "license_name": "exaone",
      "license_link": "https://huggingface.co/LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct/blob/main/LICENSE",
      "pipeline_tag": "text-generation",
      "base_model": [
        "LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct"
      ],
      "base_model_relation": "quantized",
      "tags": [
        "mobilint",
        "exaone",
        "llama-cpp",
        "gguf",
        "npu"
      ],
      "library_name": "llama-cpp"
    },
    "hero_image_url": "https://huggingface.co/mobilint/Llama-3.1-8B-Instruct/resolve/main/mobilint_logo.png",
    "summary": "This repository provides **EXAONE 3.5 2.4B Instruct** compiled and optimized for Mobilint NPU hardware, packaged for use with llama.cpp-mblt.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: other\nlicense_name: exaone\nlicense_link: https://huggingface.co/LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct/blob/main/LICENSE\npipeline_tag: text-generation\nbase_model:\n- LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct\nbase_model_relation: quantized\ntags:\n- mobilint\n- exaone\n- llama-cpp\n- gguf\n- npu\nlibrary_name: llama-cpp\n---\n\n<p align=\"center\">\n  <a href=\"https://mobilint.com\"><img src=\"https://huggingface.co/mobilint/Llama-3.1-8B-Instruct/resolve/main/mobilint_logo.png\" width=\"400\"/></a>\n</p>\n\n# EXAONE 3.5 2.4B Instruct — GGUF + MXQ for llama-cli-mblt\n\nThis repository provides **EXAONE 3.5 2.4B Instruct** compiled and optimized for Mobilint NPU hardware, packaged for use with [llama.cpp-mblt](https://git.mobilint.com/algorithm-team/integration/llama.cpp-mblt).\n\n## Branches\n\n| Branch | Contents | Description |\n|--------|----------|-------------|\n| **`main`** | Body model only | Standard autoregressive decoding |\n| **`eagle3`** | Body + FC + Draft models | EAGLE3 speculative decoding (~2-4x faster) |\n\n## Quick Start\n\n```bash\n# Simple decoding\nllama-cli-mblt -hf mobilint/EXAONE-3.5-2.4B-Instruct-GGUF -p \"Hello!\" -n 128\n\n# EAGLE3 speculative decoding\nllama-cli-mblt -hf mobilint/EXAONE-3.5-2.4B-Instruct-GGUF --eagle3 -p \"Hello!\" -n 128\n\n# Interactive chat\nllama-cli-mblt -hf mobilint/EXAONE-3.5-2.4B-Instruct-GGUF --eagle3\n```\n\n## Files\n\n### main branch\n\n| File | Size | Description |\n|------|------|-------------|\n| `exaone-3.5-2.4b-instruct-vocab.gguf` | 4.0 MB | Tokenizer (vocab-only GGUF) |\n| `target_emb.bin` | 1.0 GB | Body embedding weights (float32) |\n| `EXAONE-3.5-2.4B-Instruct.mxq` | 1.4 GB | Body model for NPU |\n| `config.json` | — | Model configuration |\n\n### eagle3 branch (adds)\n\n| File | Size | Description |\n|------|------|-------------|\n| `single_Fc_EXAONE-3.5-2.4B-Instruct.mxq` | 19 MB | FC dimension converter model |\n| `Draft_EXAONE-3.5-2.4B-Instruct.mxq` | 87 MB | EAGLE3 draft model |\n| `draft_emb.bin` | 1.0 GB | Draft embedding weights |\n| `d2t.bin` | 250 KB | Draft-to-target vocabulary mapping |\n\n## About\n\nThis model is compiled and optimized for [Mobilint NPU hardware](https://mobilint.com). It is intended to be used with `llama-cli-mblt` from [llama.cpp-mblt](https://git.mobilint.com/algorithm-team/integration/llama.cpp-mblt).\n",
    "related_quantizations": []
  },
  "tags": [
    "llama-cpp",
    "gguf",
    "mobilint-exaone",
    "mobilint",
    "exaone",
    "npu",
    "text-generation",
    "base_model:LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct",
    "base_model:quantized:LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct",
    "license:other",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 611,
  "gated": false,
  "private": false,
  "last_modified": "2026-04-08T23:49:11.000Z",
  "created_at": "2026-03-26T09:51:28.000Z",
  "pipeline_tag": "text-generation",
  "library_name": "llama-cpp"
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "69c501a054f477b388806016",
  "id": "mobilint/EXAONE-3.5-2.4B-Instruct-GGUF",
  "modelId": "mobilint/EXAONE-3.5-2.4B-Instruct-GGUF",
  "sha": "d80d2cec78250079b60c4e154270c1943b4fb838",
  "createdAt": "2026-03-26T09:51:28.000Z",
  "lastModified": "2026-04-08T23:49:11.000Z",
  "author": "mobilint",
  "downloads": 611,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "llama-cpp",
  "siblings_count": 6
}