GGUF model dataset
A free, regularly updated table of 215,180 GGUF models and 1,926,576 quant files: parameter counts, context lengths, file sizes and memory estimates. Download it as CSV for research, tools or your own comparisons.
What the dataset contains
Two linked tables. models.csv has one row per GGUF repository, with the model’s family, publisher, license, architecture, parameter count and trained context length. files.csv has one row per quant file, with its size and an estimate of the memory needed to run it. Join them on the model slug. The catalog was last updated on 2026-11-16.
Sample rows
| Model | Family | Parameters | Context | Quants | File sizes |
|---|---|---|---|---|---|
| Qwen3.8 Flash Next GSQ RCO | Qwen | 177B | 256K | 4 | 66.4 to 83.6 GB |
| Qwen3.8-27B | Qwen | 27.3B | 256K | 27 | 0.0 to 54.7 GB |
| Ornith-1.5-9B | Ornith | 9.2B | 256K | 5 | 5.8 to 18.4 GB |
| Ornith-1.5-35B | Ornith | 35.5B | 256K | 5 | 21.7 to 71.1 GB |
| Qwen3.8-27B iMatrix NVFP4 MTP | Qwen | 461M | 256K | 1 | 17.1 to 17.1 GB |
| Qwen3.8-27B | Qwen | 27.3B | 256K | 48 | 6.6 to 54.7 GB |
The most downloaded language models. The full tables are in the CSV files.
models.csv columns
| Column | Meaning |
|---|---|
slug | The model’s URL slug on ggufmodels.com |
url | The full page address |
name | Model name |
kind | language or other (image, audio and other non-language models) |
family | Model family, such as Llama or Qwen |
uploader | The Hugging Face user or organization that published the GGUF files |
hf_repo | The Hugging Face repository |
base_model | The original model the GGUF was made from, when listed |
license | License as listed on Hugging Face |
architecture | Architecture from the GGUF header, such as llama or qwen2 |
parameters_billion | Total parameters in billions (Hugging Face’s count when available) |
active_parameters_billion | Active parameters of a mixture-of-experts model, when the name states it |
is_mixture_of_experts | 1 or 0 |
context_length | Trained context length in tokens, from the GGUF header |
layers | Number of layers, from the GGUF header |
size_class | Tiny, Small, Medium or Large |
categories | Semicolon-separated: General, Coding, Vision, Reasoning, Roleplay, Embedding, Image, Audio, Other |
abilities | Semicolon-separated: tools, vision, reasoning, coding, multilingual, roleplay, embedding |
quant_count | Number of quant files in the repository |
smallest_file_gb | Size of the smallest quant file |
largest_file_gb | Size of the largest quant file |
hf_downloads | Hugging Face download count when last read |
hf_likes | Hugging Face likes |
hf_created_at | When the repository was created |
hf_updated_at | When it was last updated |
files.csv columns
| Column | Meaning |
|---|---|
model_slug | Links the file to a row in models.csv |
quant | Quant type, such as Q4_K_M |
filename | File name (the first part of a split file) |
size_bytes | Size in bytes, all parts of a split file added up |
size_gb | Size in gigabytes (109 bytes) |
est_memory_gb_8k | Estimated memory: file size + fp16 KV cache at an 8K context + 0.5 GB runtime |
parts | Number of parts the file is split into |
hf_url | The file page on Hugging Face |
License and how to cite
The dataset is released under CC BY 4.0. You may copy, redistribute and adapt it, including for commercial use, as long as you give credit. Suggested citation:
ggufmodels.com. GGUF model catalog dataset. https://ggufmodels.com/data
Model files themselves are not part of the dataset and are not hosted here. Each model keeps the license listed in its repository on Hugging Face.
Limits to keep in mind
The data is read automatically from Hugging Face and from the GGUF file headers, so a repository with an unusual layout can occasionally be misread. Parameter counts use Hugging Face’s figure when it has one, otherwise our best estimate. Memory figures are estimates. Read how the data is gathered for the full method.
Frequently asked questions
Is the GGUF model dataset free to use?
Yes. It is free to download and use, including commercially, under the CC BY 4.0 license: you only have to credit ggufmodels.com. The underlying facts, such as file names, sizes and download counts, come from Hugging Face’s public API.
How often is the dataset updated?
The files are generated from the live catalog and refreshed about once an hour. The catalog itself checks for new uploads every half hour and refreshes the whole list daily.
How are the memory estimates calculated?
Each estimate is the file size plus an fp16 KV cache for an 8K context window, computed from the model’s own header, plus 0.5 GB of runtime overhead. They are estimates, not measurements.
Does the dataset include benchmark scores?
Not yet. It describes the files and their specifications: sizes, quants, context length, parameter counts and memory estimates.