GraySoft
Download guIDE →
Projects Models About FAQ Contact Download guIDE →
Model Intelligence Sheet

richarderkhov/jaeyong2_-_qwen2.5-3b-instruct-viet-sft-gguf overview

Quantization made by Richard Erkhov. Github Discord Request more models Qwen2.5-3B-Instruct-Viet-SFT - GGUF | Name | Quant method | Size | | ---- | ---- | ---- | | Qwen2.5-3B-Instruct-Viet-SFT.Q2K.gguf | Q2K | 1.19GB | | Qwen2.5-3B-Instruct-Viet-SFT.IQ3XS.gguf | IQ3XS | 1.3GB | | Qwen2.5-3B-Instruct-Viet-SFT.IQ3S.gguf | IQ3S | 1.36GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q3KS.gguf | Q3KS | 1.35GB | | Qwen2.5-3B-Instruct-Viet-SFT.IQ3M.gguf | IQ3M | 1.39GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q3K.gguf | Q3K | 1.48GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q3KM.gguf | Q3KM | 1.48GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q3KL.gguf | Q3KL | 1.59GB | | Qwen2.5-3B-Instruct-Viet-SFT.IQ4XS.gguf | IQ4XS | 1.63GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q40.gguf | Q40 | 1.7GB | | Qwen2.5-3B-Instruct-Viet-SFT.IQ4NL.gguf | IQ4NL | 1.71GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q4KS.gguf | Q4KS | 1.71GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q4K.gguf | Q4K | 1.8GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q4KM.gguf | Q4KM | 1.8GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q41.gguf | Q41 | 1.86GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q50.gguf | Q50 | 2.02GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q5KS.gguf | Q5KS | 2.02GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q5K.gguf | Q5K | 2.07GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q5KM.gguf | Q5KM | 2.07GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q51.gguf | Q51 | 2.18GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q6K.gguf | Q6K | 2.36GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q80.gguf | Q80 | 3.06GB | Original model description: --- libraryname: transformers language: basemodel: license: other --- ### This model was trained on a Vietnamese dataset and built with Qwen. ### License Qwen/Qwen2.5-3B-Instruct : https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE ### Acknowledgement This research is supported by TPU Research Cloud program.

ggufendpoints_compatibleregion:usconversational
richarderkhov/jaeyong2_-_qwen2.5-3b-instruct-viet-sft-gguf visual
Downloads
270
Likes
0
Pipeline
—
Library
—
Visibility
Public
Access
Open

Repository Files & Downloads

22 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
Qwen2.5-3B-Instruct-Viet-SFT.IQ3_M.gguf GGUF IQ3_M 1.39 GB Download
Qwen2.5-3B-Instruct-Viet-SFT.IQ3_S.gguf GGUF IQ3_S 1.36 GB Download
Qwen2.5-3B-Instruct-Viet-SFT.IQ3_XS.gguf GGUF IQ3_XS 1.30 GB Download
Qwen2.5-3B-Instruct-Viet-SFT.IQ4_NL.gguf GGUF IQ4_NL 1.71 GB Download
Qwen2.5-3B-Instruct-Viet-SFT.IQ4_XS.gguf GGUF IQ4_XS 1.63 GB Download
Qwen2.5-3B-Instruct-Viet-SFT.Q2_K.gguf GGUF Q2_K 1.19 GB Download
Qwen2.5-3B-Instruct-Viet-SFT.Q3_K.gguf GGUF Q3_K 1.48 GB Download
Qwen2.5-3B-Instruct-Viet-SFT.Q3_K_L.gguf GGUF Q3_K_L 1.59 GB Download
Qwen2.5-3B-Instruct-Viet-SFT.Q3_K_M.gguf GGUF Q3_K_M 1.48 GB Download
Qwen2.5-3B-Instruct-Viet-SFT.Q3_K_S.gguf GGUF Q3_K_S 1.35 GB Download
Qwen2.5-3B-Instruct-Viet-SFT.Q4_0.gguf GGUF — 1.70 GB Download
Qwen2.5-3B-Instruct-Viet-SFT.Q4_1.gguf GGUF — 1.86 GB Download
Qwen2.5-3B-Instruct-Viet-SFT.Q4_K.gguf GGUF Q4_K 1.80 GB Download
Qwen2.5-3B-Instruct-Viet-SFT.Q4_K_M.gguf GGUF Q4_K_M 1.80 GB Download
Qwen2.5-3B-Instruct-Viet-SFT.Q4_K_S.gguf GGUF Q4_K_S 1.71 GB Download
Qwen2.5-3B-Instruct-Viet-SFT.Q5_0.gguf GGUF — 2.02 GB Download
Qwen2.5-3B-Instruct-Viet-SFT.Q5_1.gguf GGUF — 2.18 GB Download
Qwen2.5-3B-Instruct-Viet-SFT.Q5_K.gguf GGUF Q5_K 2.07 GB Download
Qwen2.5-3B-Instruct-Viet-SFT.Q5_K_M.gguf GGUF Q5_K_M 2.07 GB Download
Qwen2.5-3B-Instruct-Viet-SFT.Q5_K_S.gguf GGUF Q5_K_S 2.02 GB Download
Qwen2.5-3B-Instruct-Viet-SFT.Q6_K.gguf GGUF Q6_K 2.36 GB Download
Qwen2.5-3B-Instruct-Viet-SFT.Q8_0.gguf GGUF — 3.06 GB Download

Model Details Live

Model Slug
richarderkhov/jaeyong2_-_qwen2.5-3b-instruct-viet-sft-gguf
Author
RichardErkhov
Pipeline Task
—
Library
—
Created
2025-04-04
Last Modified
2025-04-04
Gated
No
Private
No
HF SHA
3859c57463952672b280ebb29f344285e17ccc53
License
Unknown
Language
Unknown
Base Model
Unknown

Metadata Inspector

Normalized metadata (stored in metadata_json) 
{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "Quantization made by Richard Erkhov. Github Discord Request more models Qwen2.5-3B-Instruct-Viet-SFT - GGUF | Name | Quant method | Size | | ---- | ---- | ---- | | Qwen2.5-3B-Instruct-Viet-SFT.Q2_K.gguf | Q2_K | 1.19GB | | Qwen2.5-3B-Instruct-Viet-SFT.IQ3_XS.gguf | IQ3_XS | 1.3GB | | Qwen2.5-3B-Instruct-Viet-SFT.IQ3_S.gguf | IQ3_S | 1.36GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q3_K_S.gguf | Q3_K_S | 1.35GB | | Qwen2.5-3B-Instruct-Viet-SFT.IQ3_M.gguf | IQ3_M | 1.39GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q3_K.gguf | Q3_K | 1.48GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q3_K_M.gguf | Q3_K_M | 1.48GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q3_K_L.gguf | Q3_K_L | 1.59GB | | Qwen2.5-3B-Instruct-Viet-SFT.IQ4_XS.gguf | IQ4_XS | 1.63GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q4_0.gguf | Q4_0 | 1.7GB | | Qwen2.5-3B-Instruct-Viet-SFT.IQ4_NL.gguf | IQ4_NL | 1.71GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q4_K_S.gguf | Q4_K_S | 1.71GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q4_K.gguf | Q4_K | 1.8GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q4_K_M.gguf | Q4_K_M | 1.8GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q4_1.gguf | Q4_1 | 1.86GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q5_0.gguf | Q5_0 | 2.02GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q5_K_S.gguf | Q5_K_S | 2.02GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q5_K.gguf | Q5_K | 2.07GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q5_K_M.gguf | Q5_K_M | 2.07GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q5_1.gguf | Q5_1 | 2.18GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q6_K.gguf | Q6_K | 2.36GB | | Qwen2.5-3B-Instruct-Viet-SFT.Q8_0.gguf | Q8_0 | 3.06GB | Original model description: --- library_name: transformers language: base_model: license: other --- ### This model was trained on a Vietnamese dataset and built with Qwen. ### License Qwen/Qwen2.5-3B-Instruct : https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE ### Acknowledgement This research is supported by TPU Research Cloud program.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "Quantization made by Richard Erkhov.\n\n[Github](https://github.com/RichardErkhov)\n\n[Discord](https://discord.gg/pvy7H8DZMG)\n\n[Request more models](https://github.com/RichardErkhov/quant_request)\n\n\nQwen2.5-3B-Instruct-Viet-SFT - GGUF\n- Model creator: https://huggingface.co/jaeyong2/\n- Original model: https://huggingface.co/jaeyong2/Qwen2.5-3B-Instruct-Viet-SFT/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Qwen2.5-3B-Instruct-Viet-SFT.Q2_K.gguf](https://huggingface.co/RichardErkhov/jaeyong2_-_Qwen2.5-3B-Instruct-Viet-SFT-gguf/blob/main/Qwen2.5-3B-Instruct-Viet-SFT.Q2_K.gguf) | Q2_K | 1.19GB |\n| [Qwen2.5-3B-Instruct-Viet-SFT.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/jaeyong2_-_Qwen2.5-3B-Instruct-Viet-SFT-gguf/blob/main/Qwen2.5-3B-Instruct-Viet-SFT.IQ3_XS.gguf) | IQ3_XS | 1.3GB |\n| [Qwen2.5-3B-Instruct-Viet-SFT.IQ3_S.gguf](https://huggingface.co/RichardErkhov/jaeyong2_-_Qwen2.5-3B-Instruct-Viet-SFT-gguf/blob/main/Qwen2.5-3B-Instruct-Viet-SFT.IQ3_S.gguf) | IQ3_S | 1.36GB |\n| [Qwen2.5-3B-Instruct-Viet-SFT.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/jaeyong2_-_Qwen2.5-3B-Instruct-Viet-SFT-gguf/blob/main/Qwen2.5-3B-Instruct-Viet-SFT.Q3_K_S.gguf) | Q3_K_S | 1.35GB |\n| [Qwen2.5-3B-Instruct-Viet-SFT.IQ3_M.gguf](https://huggingface.co/RichardErkhov/jaeyong2_-_Qwen2.5-3B-Instruct-Viet-SFT-gguf/blob/main/Qwen2.5-3B-Instruct-Viet-SFT.IQ3_M.gguf) | IQ3_M | 1.39GB |\n| [Qwen2.5-3B-Instruct-Viet-SFT.Q3_K.gguf](https://huggingface.co/RichardErkhov/jaeyong2_-_Qwen2.5-3B-Instruct-Viet-SFT-gguf/blob/main/Qwen2.5-3B-Instruct-Viet-SFT.Q3_K.gguf) | Q3_K | 1.48GB |\n| [Qwen2.5-3B-Instruct-Viet-SFT.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/jaeyong2_-_Qwen2.5-3B-Instruct-Viet-SFT-gguf/blob/main/Qwen2.5-3B-Instruct-Viet-SFT.Q3_K_M.gguf) | Q3_K_M | 1.48GB |\n| [Qwen2.5-3B-Instruct-Viet-SFT.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/jaeyong2_-_Qwen2.5-3B-Instruct-Viet-SFT-gguf/blob/main/Qwen2.5-3B-Instruct-Viet-SFT.Q3_K_L.gguf) | Q3_K_L | 1.59GB |\n| [Qwen2.5-3B-Instruct-Viet-SFT.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/jaeyong2_-_Qwen2.5-3B-Instruct-Viet-SFT-gguf/blob/main/Qwen2.5-3B-Instruct-Viet-SFT.IQ4_XS.gguf) | IQ4_XS | 1.63GB |\n| [Qwen2.5-3B-Instruct-Viet-SFT.Q4_0.gguf](https://huggingface.co/RichardErkhov/jaeyong2_-_Qwen2.5-3B-Instruct-Viet-SFT-gguf/blob/main/Qwen2.5-3B-Instruct-Viet-SFT.Q4_0.gguf) | Q4_0 | 1.7GB |\n| [Qwen2.5-3B-Instruct-Viet-SFT.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/jaeyong2_-_Qwen2.5-3B-Instruct-Viet-SFT-gguf/blob/main/Qwen2.5-3B-Instruct-Viet-SFT.IQ4_NL.gguf) | IQ4_NL | 1.71GB |\n| [Qwen2.5-3B-Instruct-Viet-SFT.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/jaeyong2_-_Qwen2.5-3B-Instruct-Viet-SFT-gguf/blob/main/Qwen2.5-3B-Instruct-Viet-SFT.Q4_K_S.gguf) | Q4_K_S | 1.71GB |\n| [Qwen2.5-3B-Instruct-Viet-SFT.Q4_K.gguf](https://huggingface.co/RichardErkhov/jaeyong2_-_Qwen2.5-3B-Instruct-Viet-SFT-gguf/blob/main/Qwen2.5-3B-Instruct-Viet-SFT.Q4_K.gguf) | Q4_K | 1.8GB |\n| [Qwen2.5-3B-Instruct-Viet-SFT.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/jaeyong2_-_Qwen2.5-3B-Instruct-Viet-SFT-gguf/blob/main/Qwen2.5-3B-Instruct-Viet-SFT.Q4_K_M.gguf) | Q4_K_M | 1.8GB |\n| [Qwen2.5-3B-Instruct-Viet-SFT.Q4_1.gguf](https://huggingface.co/RichardErkhov/jaeyong2_-_Qwen2.5-3B-Instruct-Viet-SFT-gguf/blob/main/Qwen2.5-3B-Instruct-Viet-SFT.Q4_1.gguf) | Q4_1 | 1.86GB |\n| [Qwen2.5-3B-Instruct-Viet-SFT.Q5_0.gguf](https://huggingface.co/RichardErkhov/jaeyong2_-_Qwen2.5-3B-Instruct-Viet-SFT-gguf/blob/main/Qwen2.5-3B-Instruct-Viet-SFT.Q5_0.gguf) | Q5_0 | 2.02GB |\n| [Qwen2.5-3B-Instruct-Viet-SFT.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/jaeyong2_-_Qwen2.5-3B-Instruct-Viet-SFT-gguf/blob/main/Qwen2.5-3B-Instruct-Viet-SFT.Q5_K_S.gguf) | Q5_K_S | 2.02GB |\n| [Qwen2.5-3B-Instruct-Viet-SFT.Q5_K.gguf](https://huggingface.co/RichardErkhov/jaeyong2_-_Qwen2.5-3B-Instruct-Viet-SFT-gguf/blob/main/Qwen2.5-3B-Instruct-Viet-SFT.Q5_K.gguf) | Q5_K | 2.07GB |\n| [Qwen2.5-3B-Instruct-Viet-SFT.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/jaeyong2_-_Qwen2.5-3B-Instruct-Viet-SFT-gguf/blob/main/Qwen2.5-3B-Instruct-Viet-SFT.Q5_K_M.gguf) | Q5_K_M | 2.07GB |\n| [Qwen2.5-3B-Instruct-Viet-SFT.Q5_1.gguf](https://huggingface.co/RichardErkhov/jaeyong2_-_Qwen2.5-3B-Instruct-Viet-SFT-gguf/blob/main/Qwen2.5-3B-Instruct-Viet-SFT.Q5_1.gguf) | Q5_1 | 2.18GB |\n| [Qwen2.5-3B-Instruct-Viet-SFT.Q6_K.gguf](https://huggingface.co/RichardErkhov/jaeyong2_-_Qwen2.5-3B-Instruct-Viet-SFT-gguf/blob/main/Qwen2.5-3B-Instruct-Viet-SFT.Q6_K.gguf) | Q6_K | 2.36GB |\n| [Qwen2.5-3B-Instruct-Viet-SFT.Q8_0.gguf](https://huggingface.co/RichardErkhov/jaeyong2_-_Qwen2.5-3B-Instruct-Viet-SFT-gguf/blob/main/Qwen2.5-3B-Instruct-Viet-SFT.Q8_0.gguf) | Q8_0 | 3.06GB |\n\n\n\n\nOriginal model description:\n---\nlibrary_name: transformers\nlanguage:\n- vi\n- en\nbase_model:\n- Qwen/Qwen2.5-3B-Instruct\nlicense: other\n---\n\n### This model was trained on a Vietnamese dataset and built with Qwen.\n\n### License\nQwen/Qwen2.5-3B-Instruct : https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE\n\n### Acknowledgement\nThis research is supported by TPU Research Cloud program.\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 270,
  "gated": false,
  "private": false,
  "last_modified": "2025-04-04T16:40:49.000Z",
  "created_at": "2025-04-04T16:07:25.000Z",
  "pipeline_tag": "",
  "library_name": ""
}
Source payload excerpt (from Hugging Face API) 
{
  "_id": "67f003bd22862adf90710d98",
  "id": "RichardErkhov/jaeyong2_-_Qwen2.5-3B-Instruct-Viet-SFT-gguf",
  "modelId": "RichardErkhov/jaeyong2_-_Qwen2.5-3B-Instruct-Viet-SFT-gguf",
  "sha": "3859c57463952672b280ebb29f344285e17ccc53",
  "createdAt": "2025-04-04T16:07:25.000Z",
  "lastModified": "2025-04-04T16:40:49.000Z",
  "author": "RichardErkhov",
  "downloads": 270,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}