<div align="center">

<a href="https://h9-tec.github.io/model-family-tree/galaxy.html"><img src="assets/galaxy.jpg" alt="The Model Galaxy: every Hugging Face model with an ancestor or a descendant, as one zoomable map. Families are clusters, base models are stars, derivatives are the dots around them." width="100%"/></a>

**[Fly through the Model Galaxy →](https://h9-tec.github.io/model-family-tree/galaxy.html)** · 967,694 models in one zoomable WebGL map · **[Explorer →](https://h9-tec.github.io/model-family-tree/)** · search any model, walk its pedigree, share a link.

# Open Model Family Tree

**Every model on the Hugging Face Hub, its ancestry, and a leaderboard of the base models the ecosystem actually builds on. Rebuilt nightly.**

![Models](https://img.shields.io/badge/models-3218k-0A7E8C)
![Links](https://img.shields.io/badge/parent%20links-954k-0A7E8C)
![Updated](https://img.shields.io/badge/updated-2026--11--07-555)
[![Stars](https://img.shields.io/github/stars/h9-tec/model-family-tree?style=flat)](https://github.com/h9-tec/model-family-tree/stargazers)
[![License: MIT](https://img.shields.io/badge/license-MIT-green)](LICENSE)

</div>

**3,218,866** models · **921,536** declare a base model (29%) · **954,781** parent links · **91,142** models have descendants · **46,120** roots in **24,638** families

The most built-on model on the Hub is **[black-forest-labs/FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev)** with **43,722** descendants. In the last 90 days it is **[Qwen/Qwen3.8-27B](https://huggingface.co/Qwen/Qwen3.8-27B)** with **5,545** new ones. The biggest family is **Qwen2.5** (71,238).

## Install into your agent

```bash
claude plugin marketplace add h9-tec/model-family-tree
claude plugin install model-family-tree@model-family-tree
```

Requires [uv](https://docs.astral.sh/uv/) on PATH. Then ask Claude: *what is unsloth/Qwen2.5-7B-Instruct based on, and which Qwen base has the most finetunes?* It answers from the `lineage` and `leaderboard` MCP tools.

<details>
<summary>Any MCP client</summary>

```json
{"mcpServers": {"model-family-tree": {"command": "uv", "args": ["run", "--frozen", "--no-dev", "--directory", "/path/to/model-family-tree", "python", "mcp/server.py"]}}}
```

Tools: `lineage(id)`, `children(id)`, `leaderboard(kind)`, `family(name)`, `search(query)`.

</details>

## See it

| | |
|---|---|
| **[Galaxy](https://h9-tec.github.io/model-family-tree/galaxy.html)** | Every model that has an ancestor or a descendant (967,694 points) in one WebGL map. Families are circle-packed clusters, base models are stars, each derivative is a dot colored by relation and sized by downloads. Scroll to zoom from the whole Hub down to one model, click any dot. |
| **[Explorer](https://h9-tec.github.io/model-family-tree/)** | Type any model id. Its pedigree is drawn as a radial tree: every ancestor path fans out to the left (merges show all parents), the most downloaded descendants to the right, unfoldable level by level, live from the Hub. |
| **[Leaderboard](https://h9-tec.github.io/model-family-tree/#board:all)** | All 91,142 models with descendants, sortable and filterable, plus the curated views below. |

<a href="assets/families.svg"><img src="assets/families.svg" alt="Cumulative descendants per model family over the last 24 months" width="100%"/></a>

## Most-descended base models

Unique descendants of every kind: finetunes, adapters (LoRA), quantizations and merges, each counted once however many paths reach it. † marks a base that was deleted or made private but is still referenced. [Full top 500 →](docs/tables/models_all_time.md)

| # | Model | Descendants | Direct | Last 90d | Finetune / adapter / quantized / merge | Family |
|---:|---|---:|---:|---:|---|---|
| 1 | [black-forest-labs/FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev) | 43,722 | 43,443 | 235 | 692 / 42,877 / 137 / 16 | FLUX.1 |
| 2 | [Qwen/Qwen1.5-0.5B](https://huggingface.co/Qwen/Qwen1.5-0.5B) | 32,564 | 32,534 | 0 | 41 / 32,475 / 46 / 2 | Qwen1.5 |
| 3 | [Qwen/Qwen1.5-1.8B](https://huggingface.co/Qwen/Qwen1.5-1.8B) | 30,658 | 30,628 | 2 | 36 / 30,591 / 29 / 2 | Qwen1.5 |
| 4 | [google/gemma-2b](https://huggingface.co/google/gemma-2b) | 24,117 | 24,037 | 8 | 311 / 23,706 / 89 / 11 | Gemma 1 |
| 5 | [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) | 23,161 | 2,088 | 2,380 | 12,056 / 6,972 / 3,542 / 591 | Qwen2.5 |
| 6 | [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) | 21,772 | 3,275 | 2,110 | 9,619 / 6,158 / 5,148 / 847 | Llama 3.1 |
| 7 | [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) | 15,329 | 7,401 | 1,508 | 6,916 / 4,083 / 3,615 / 715 | Llama 3.1 |
| 8 | [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) | 14,695 | 6,768 | 1,778 | 8,536 / 3,946 / 1,804 / 409 | Qwen2.5 |
| 9 | [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) | 13,714 | 13,332 | 738 | 13,163 / 398 / 152 / 1 | DistilBERT |
| 10 | [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) | 11,622 | 4,017 | 72 | 2,983 / 5,192 / 2,067 / 1,365 | Mistral |
| 11 | [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) | 11,566 | 11,080 | 218 | 1,423 / 10,034 / 55 / 54 | Stable Diffusion |
| 12 | [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) | 11,384 | 9,035 | 1,664 | 3,604 / 6,577 / 1,112 / 91 | Qwen3 |
| 13 | [Qwen/Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B) | 11,285 | 1,078 | 1,819 | 5,116 / 4,230 / 1,776 / 163 | Qwen2.5 |
| 14 | [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) | 10,284 | 1,730 | 73 | 4,210 / 2,074 / 3,012 / 988 | Llama 3 |
| 15 | [HuggingFaceTB/SmolLM2-360M](https://huggingface.co/HuggingFaceTB/SmolLM2-360M) | 9,990 | 204 | 1,655 | 9,001 / 624 / 360 / 5 | SmolLM2 |
| 16 | [google/gemma-7b](https://huggingface.co/google/gemma-7b) | 9,857 | 9,587 | 6 | 456 / 9,296 / 97 / 8 | Gemma 1 |
| 17 | [Qwen/Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B) | 9,834 | 1,389 | 1,116 | 6,086 / 2,331 / 1,360 / 57 | Qwen2.5 |
| 18 | [Qwen/Qwen3-8B-Base](https://huggingface.co/Qwen/Qwen3-8B-Base) | 9,832 | 887 | 2,009 | 4,908 / 3,010 / 1,841 / 72 | Qwen3 |
| 19 | [HuggingFaceTB/SmolLM2-360M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct) | 9,520 | 408 | 1,614 | 8,837 / 392 / 286 / 5 | SmolLM2 |
| 20 | [HuggingFaceTB/SmolVLM-500M-Instruct](https://huggingface.co/HuggingFaceTB/SmolVLM-500M-Instruct) | 8,807 | 93 | 1,489 | 8,588 / 153 / 66 / 0 | SmolLM2 |
| 21 | [Qwen/Qwen2.5-3B](https://huggingface.co/Qwen/Qwen2.5-3B) | 8,727 | 1,138 | 1,272 | 3,909 / 3,181 / 1,552 / 85 | Qwen2.5 |
| 22 | [HuggingFaceTB/SmolVLM2-500M-Video-Instruct](https://huggingface.co/HuggingFaceTB/SmolVLM2-500M-Video-Instruct) | 8,705 | 132 | 1,470 | 8,553 / 122 / 30 / 0 | SmolLM2 |
| 23 | [lerobot/smolvla_base](https://huggingface.co/lerobot/smolvla_base) | 8,569 | 8,506 | 1,450 | 8,459 / 104 / 6 / 0 | SmolLM2 |
| 24 | [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) | 8,136 | 5,274 | 1,567 | 3,762 / 2,787 / 1,518 / 68 | Qwen3 |
| 25 | [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) | 7,568 | 3,509 | 521 | 3,946 / 1,604 / 1,866 / 152 | Llama 3.2 |

## Hot right now: new descendants in the last 90 days

[Full top 500 →](docs/tables/models_90d.md)

| # | Model | Descendants | Direct | Last 90d | Finetune / adapter / quantized / merge | Family |
|---:|---|---:|---:|---:|---|---|
| 1 | [Qwen/Qwen3.8-27B](https://huggingface.co/Qwen/Qwen3.8-27B) | 5,554 | 2,837 | 5,545 | 1,246 / 462 / 3,785 / 61 | Qwen3.8 |
| 2 | [Qwen/Qwen3.5-9B-Base](https://huggingface.co/Qwen/Qwen3.5-9B-Base) | 6,712 | 798 | 3,439 | 2,637 / 1,523 / 2,447 / 105 | Qwen3.5 |
| 3 | [Qwen/Qwen3.5-4B-Base](https://huggingface.co/Qwen/Qwen3.5-4B-Base) | 5,566 | 457 | 3,229 | 2,146 / 1,569 / 1,801 / 50 | Qwen3.5 |
| 4 | [Qwen/Qwen3.5-4B](https://huggingface.co/Qwen/Qwen3.5-4B) | 4,923 | 2,949 | 2,799 | 1,813 / 1,401 / 1,664 / 45 | Qwen3.5 |
| 5 | [Qwen/Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B) | 5,552 | 3,021 | 2,753 | 1,827 / 1,414 / 2,209 / 102 | Qwen3.5 |
| 6 | [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) | 23,161 | 2,088 | 2,380 | 12,056 / 6,972 / 3,542 / 591 | Qwen2.5 |
| 7 | [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) | 21,772 | 3,275 | 2,110 | 9,619 / 6,158 / 5,148 / 847 | Llama 3.1 |
| 8 | [Qwen/Qwen3-8B-Base](https://huggingface.co/Qwen/Qwen3-8B-Base) | 9,832 | 887 | 2,009 | 4,908 / 3,010 / 1,841 / 72 | Qwen3 |
| 9 | [Qwen/Qwen3.5-0.8B-Base](https://huggingface.co/Qwen/Qwen3.5-0.8B-Base) | 3,191 | 289 | 1,842 | 1,183 / 990 / 1,008 / 10 | Qwen3.5 |
| 10 | [Qwen/Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B) | 11,285 | 1,078 | 1,819 | 5,116 / 4,230 / 1,776 / 163 | Qwen2.5 |
| 11 | [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) | 14,695 | 6,768 | 1,778 | 8,536 / 3,946 / 1,804 / 409 | Qwen2.5 |
| 12 | [Qwen/Qwen3-0.6B-Base](https://huggingface.co/Qwen/Qwen3-0.6B-Base) | 6,828 | 959 | 1,675 | 3,953 / 1,047 / 1,803 / 25 | Qwen3 |
| 13 | [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) | 11,384 | 9,035 | 1,664 | 3,604 / 6,577 / 1,112 / 91 | Qwen3 |
| 14 | [HuggingFaceTB/SmolLM2-360M](https://huggingface.co/HuggingFaceTB/SmolLM2-360M) | 9,990 | 204 | 1,655 | 9,001 / 624 / 360 / 5 | SmolLM2 |
| 15 | [HuggingFaceTB/SmolLM2-360M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct) | 9,520 | 408 | 1,614 | 8,837 / 392 / 286 / 5 | SmolLM2 |
| 16 | [Qwen/Qwen3.5-0.8B](https://huggingface.co/Qwen/Qwen3.5-0.8B) | 2,754 | 1,830 | 1,580 | 993 / 905 / 848 / 8 | Qwen3.5 |
| 17 | [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) | 8,136 | 5,274 | 1,567 | 3,762 / 2,787 / 1,518 / 68 | Qwen3 |
| 18 | [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) | 15,329 | 7,401 | 1,508 | 6,916 / 4,083 / 3,615 / 715 | Llama 3.1 |
| 19 | [HuggingFaceTB/SmolVLM-500M-Instruct](https://huggingface.co/HuggingFaceTB/SmolVLM-500M-Instruct) | 8,807 | 93 | 1,489 | 8,588 / 153 / 66 / 0 | SmolLM2 |
| 20 | [HuggingFaceTB/SmolVLM2-500M-Video-Instruct](https://huggingface.co/HuggingFaceTB/SmolVLM2-500M-Video-Instruct) | 8,705 | 132 | 1,470 | 8,553 / 122 / 30 / 0 | SmolLM2 |
| 21 | [lerobot/smolvla_base](https://huggingface.co/lerobot/smolvla_base) | 8,569 | 8,506 | 1,450 | 8,459 / 104 / 6 / 0 | SmolLM2 |
| 22 | [Qwen/Qwen3-1.7B-Base](https://huggingface.co/Qwen/Qwen3-1.7B-Base) | 5,164 | 651 | 1,309 | 2,862 / 1,089 / 1,193 / 20 | Qwen3 |
| 23 | [Qwen/Qwen2.5-3B](https://huggingface.co/Qwen/Qwen2.5-3B) | 8,727 | 1,138 | 1,272 | 3,909 / 3,181 / 1,552 / 85 | Qwen2.5 |
| 24 | [Qwen/Qwen3-4B-Base](https://huggingface.co/Qwen/Qwen3-4B-Base) | 6,933 | 734 | 1,265 | 3,500 / 1,692 / 1,648 / 93 | Qwen3 |
| 25 | [Qwen/Qwen3.5-2B-Base](https://huggingface.co/Qwen/Qwen3.5-2B-Base) | 2,460 | 209 | 1,247 | 1,127 / 517 / 810 / 6 | Qwen3.5 |

## Finetunes only

Adapters and quantizations inflate the all-time table (tens of thousands of auto-generated LoRAs sit on a few small bases). This view counts descendants whose own relation to their parent is `finetune`. [Full top 500 →](docs/tables/models_finetune.md)

| # | Model | Descendants | Direct | Last 90d | Finetune / adapter / quantized / merge | Family |
|---:|---|---:|---:|---:|---|---|
| 1 | [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) | 13,714 | 13,332 | 738 | 13,163 / 398 / 152 / 1 | DistilBERT |
| 2 | [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) | 23,161 | 2,088 | 2,380 | 12,056 / 6,972 / 3,542 / 591 | Qwen2.5 |
| 3 | [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) | 21,772 | 3,275 | 2,110 | 9,619 / 6,158 / 5,148 / 847 | Llama 3.1 |
| 4 | [HuggingFaceTB/SmolLM2-360M](https://huggingface.co/HuggingFaceTB/SmolLM2-360M) | 9,990 | 204 | 1,655 | 9,001 / 624 / 360 / 5 | SmolLM2 |
| 5 | [HuggingFaceTB/SmolLM2-360M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct) | 9,520 | 408 | 1,614 | 8,837 / 392 / 286 / 5 | SmolLM2 |
| 6 | [HuggingFaceTB/SmolVLM-500M-Instruct](https://huggingface.co/HuggingFaceTB/SmolVLM-500M-Instruct) | 8,807 | 93 | 1,489 | 8,588 / 153 / 66 / 0 | SmolLM2 |
| 7 | [HuggingFaceTB/SmolVLM2-500M-Video-Instruct](https://huggingface.co/HuggingFaceTB/SmolVLM2-500M-Video-Instruct) | 8,705 | 132 | 1,470 | 8,553 / 122 / 30 / 0 | SmolLM2 |
| 8 | [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) | 14,695 | 6,768 | 1,778 | 8,536 / 3,946 / 1,804 / 409 | Qwen2.5 |
| 9 | [lerobot/smolvla_base](https://huggingface.co/lerobot/smolvla_base) | 8,569 | 8,506 | 1,450 | 8,459 / 104 / 6 / 0 | SmolLM2 |
| 10 | [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) | 7,510 | 7,265 | 289 | 7,274 / 147 / 82 / 7 | BERT |
| 11 | [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) | 15,329 | 7,401 | 1,508 | 6,916 / 4,083 / 3,615 / 715 | Llama 3.1 |
| 12 | [Qwen/Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B) | 9,834 | 1,389 | 1,116 | 6,086 / 2,331 / 1,360 / 57 | Qwen2.5 |
| 13 | [Qwen/Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B) | 11,285 | 1,078 | 1,819 | 5,116 / 4,230 / 1,776 / 163 | Qwen2.5 |
| 14 | [Qwen/Qwen3-8B-Base](https://huggingface.co/Qwen/Qwen3-8B-Base) | 9,832 | 887 | 2,009 | 4,908 / 3,010 / 1,841 / 72 | Qwen3 |
| 15 | [unsloth/Qwen2.5-7B-Instruct](https://huggingface.co/unsloth/Qwen2.5-7B-Instruct) | 5,465 | 5,423 | 613 | 4,661 / 772 / 30 / 2 | Qwen2.5 |
| 16 | [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) | 4,787 | 4,424 | 217 | 4,585 / 79 / 122 / 0 | XLM-RoBERTa |
| 17 | [google/gemma-3-4b-pt](https://huggingface.co/google/gemma-3-4b-pt) | 6,746 | 397 | 488 | 4,556 / 964 / 1,210 / 16 | Gemma 3 |
| 18 | [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) | 10,284 | 1,730 | 73 | 4,210 / 2,074 / 3,012 / 988 | Llama 3 |
| 19 | [openai/whisper-small](https://huggingface.co/openai/whisper-small) | 4,794 | 4,447 | 346 | 4,105 / 353 / 336 / 0 | Whisper |
| 20 | [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) | 4,115 | 4,059 | 13 | 4,105 / 5 / 5 / 0 | BERT |
| 21 | [Qwen/Qwen3-0.6B-Base](https://huggingface.co/Qwen/Qwen3-0.6B-Base) | 6,828 | 959 | 1,675 | 3,953 / 1,047 / 1,803 / 25 | Qwen3 |
| 22 | [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) | 7,568 | 3,509 | 521 | 3,946 / 1,604 / 1,866 / 152 | Llama 3.2 |
| 23 | [Qwen/Qwen2.5-3B](https://huggingface.co/Qwen/Qwen2.5-3B) | 8,727 | 1,138 | 1,272 | 3,909 / 3,181 / 1,552 / 85 | Qwen2.5 |
| 24 | [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) | 8,136 | 5,274 | 1,567 | 3,762 / 2,787 / 1,518 / 68 | Qwen3 |
| 25 | [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) | 11,384 | 9,035 | 1,664 | 3,604 / 6,577 / 1,112 / 91 | Qwen3 |

## Families

Roots grouped by series name across organizations (so `unsloth/Llama-3.1-8B` re-uploads count toward Llama 3.1). Grouping is a heuristic with hand overrides in [`data/families.yaml`](data/families.yaml); PRs welcome. [Full table →](docs/tables/families.md)

<a href="assets/monthly.svg"><img src="assets/monthly.svg" alt="New derivatives per month for the top families" width="100%"/></a>

| # | Family | Descendants | Last 90d | Roots | Finetune / adapter / quantized / merge | Biggest root |
|---:|---|---:|---:|---:|---|---|
| 1 | **Qwen2.5** | 71,238 | 7,741 | 689 | 34,396 / 20,396 / 14,814 / 1,632 | [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) |
| 2 | **Qwen1.5** | 71,026 | 10 | 44 | 225 / 70,436 / 349 / 16 | [Qwen/Qwen1.5-0.5B](https://huggingface.co/Qwen/Qwen1.5-0.5B) |
| 3 | **Qwen3** | 56,178 | 10,306 | 653 | 25,078 / 17,452 / 13,215 / 431 | [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) |
| 4 | **FLUX.1** | 44,185 | 262 | 16 | 785 / 43,182 / 201 / 17 | [black-forest-labs/FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev) |
| 5 | **Gemma 1** | 37,079 | 61 | 184 | 1,758 / 34,366 / 887 / 68 | [google/gemma-2b](https://huggingface.co/google/gemma-2b) |
| 6 | **Mistral** | 36,603 | 977 | 584 | 10,674 / 11,260 / 11,720 / 2,933 | [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) |
| 7 | **Llama 3.1** | 28,384 | 2,286 | 222 | 11,151 / 7,051 / 8,239 / 1,943 | [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) |
| 8 | **Llama 3** | 24,238 | 414 | 544 | 8,114 / 5,868 / 7,793 / 2,463 | [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) |
| 9 | **BERT** | 23,327 | 659 | 305 | 22,527 / 508 / 284 / 8 | [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) |
| 10 | **Qwen3.5** | 21,741 | 10,536 | 156 | 8,190 / 5,063 / 8,246 / 241 | [Qwen/Qwen3.5-9B-Base](https://huggingface.co/Qwen/Qwen3.5-9B-Base) |
| 11 | **Llama 3.2** | 21,133 | 1,173 | 477 | 9,740 / 5,669 / 5,129 / 595 | [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) |
| 12 | **Gemma 3** | 18,306 | 1,248 | 141 | 10,648 / 3,024 / 4,415 / 219 | [google/gemma-3-4b-pt](https://huggingface.co/google/gemma-3-4b-pt) |
| 13 | **Stable Diffusion** | 18,011 | 433 | 30 | 3,431 / 14,397 / 109 / 74 | [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) |
| 14 | **Whisper** | 15,857 | 1,636 | 203 | 11,723 / 2,355 / 1,772 / 7 | [openai/whisper-small](https://huggingface.co/openai/whisper-small) |
| 15 | **DistilBERT** | 15,300 | 798 | 81 | 14,518 / 498 / 283 / 1 | [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) |
| 16 | **SmolLM2** | 13,957 | 2,039 | 60 | 11,138 / 1,645 / 1,154 / 20 | [HuggingFaceTB/SmolLM2-360M](https://huggingface.co/HuggingFaceTB/SmolLM2-360M) |
| 17 | **Gemma 2** | 12,376 | 356 | 226 | 5,099 / 3,186 / 3,149 / 942 | [google/gemma-2-9b](https://huggingface.co/google/gemma-2-9b) |
| 18 | **Gemma 4** | 11,962 | 4,176 | 136 | 3,577 / 2,154 / 6,053 / 178 | [google/gemma-4-E4B](https://huggingface.co/google/gemma-4-E4B) |
| 19 | **Llama 2** | 11,631 | 257 | 412 | 2,971 / 7,073 / 1,374 / 213 | [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) |
| 20 | **Qwen2** | 10,802 | 177 | 161 | 3,183 / 6,043 / 1,488 / 88 | [Qwen/Qwen2-0.5B](https://huggingface.co/Qwen/Qwen2-0.5B) |
| 21 | **DeepSeek-R1** | 9,107 | 573 | 130 | 2,876 / 1,528 / 3,807 / 896 | [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) |
| 22 | **Qwen3.8** | 6,987 | 6,975 | 70 | 1,466 / 475 / 4,968 / 78 | [Qwen/Qwen3.8-27B](https://huggingface.co/Qwen/Qwen3.8-27B) |
| 23 | **XLM-RoBERTa** | 6,416 | 358 | 49 | 6,093 / 138 / 184 / 0 | [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) |
| 24 | **Qwen3.6** | 6,193 | 1,897 | 54 | 1,176 / 1,171 / 3,746 / 93 | [Qwen/Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B) |
| 25 | **ViT** | 6,134 | 181 | 72 | 5,242 / 752 / 140 / 0 | [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) |

## Organizations

Descendants of every root owned by the organization, deduplicated. [Full table →](docs/tables/orgs.md)

| # | Organization | Descendants of its roots | Last 90d | Roots | Biggest root |
|---:|---|---:|---:|---:|---|
| 1 | [Qwen](https://huggingface.co/Qwen) | 242,152 | 38,480 | 148 | [Qwen/Qwen1.5-0.5B](https://huggingface.co/Qwen/Qwen1.5-0.5B) |
| 2 | [google](https://huggingface.co/google) | 93,162 | 7,482 | 327 | [google/gemma-2b](https://huggingface.co/google/gemma-2b) |
| 3 | [meta-llama](https://huggingface.co/meta-llama) | 69,120 | 3,959 | 50 | [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) |
| 4 | [black-forest-labs](https://huggingface.co/black-forest-labs) | 46,232 | 770 | 20 | [black-forest-labs/FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev) |
| 5 | [mistralai](https://huggingface.co/mistralai) | 32,941 | 1,341 | 33 | [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) |
| 6 | [unsloth](https://huggingface.co/unsloth) | 24,255 | 321 | 269 | [unsloth/llama-3-8b-Instruct-bnb-4bit](https://huggingface.co/unsloth/llama-3-8b-Instruct-bnb-4bit) |
| 7 | [microsoft](https://huggingface.co/microsoft) | 22,526 | 1,148 | 256 | [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) |
| 8 | [openai](https://huggingface.co/openai) | 19,662 | 2,049 | 21 | [openai/whisper-small](https://huggingface.co/openai/whisper-small) |
| 9 | [facebook](https://huggingface.co/facebook) | 17,942 | 1,279 | 507 | [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) |
| 10 | [distilbert](https://huggingface.co/distilbert) | 17,653 | 924 | 9 | [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) |
| 11 | [HuggingFaceTB](https://huggingface.co/HuggingFaceTB) | 16,625 | 2,244 | 29 | [HuggingFaceTB/SmolLM2-360M](https://huggingface.co/HuggingFaceTB/SmolLM2-360M) |
| 12 | [stabilityai](https://huggingface.co/stabilityai) | 15,315 | 324 | 73 | [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) |
| 13 | [google-bert](https://huggingface.co/google-bert) | 14,763 | 402 | 12 | [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) |
| 14 | [deepseek-ai](https://huggingface.co/deepseek-ai) | 14,625 | 1,604 | 78 | [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) |
| 15 | [FacebookAI](https://huggingface.co/FacebookAI) | 10,025 | 500 | 19 | [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) |

## How it works

1. **Source.** The daily [`cfahlgren1/hub-stats`](https://huggingface.co/datasets/cfahlgren1/hub-stats) dump of the Hub's `/api/models` (Apache-2.0), which carries the `base_model` metadata model authors declare in their cards, plus the legacy `base_model:` tags as a fallback.
2. **Graph.** Child → parent edges with the declared relation (`finetune`, `adapter`, `quantized`, `merge`). Merges give a DAG, mis-tagged cards give the occasional cycle (78 nodes today); both are handled.
3. **Counts.** Descendant sets are built children-first and unioned, so every model is counted once per ancestor. `direct` is declared children; `total` is the whole subtree.
4. **Families.** Roots (models that declare no parent) are grouped by a series heuristic over the model name, with overrides in `data/families.yaml`.
5. **Galaxy layout.** Each root's subtree is a radial tree (depth rings sized by population, wedges by subtree size); roots are circle-packed inside their family and families into the galaxy, with a port of d3's front-chain packing. Positions ship as a 10 MB binary, ids load lazily in chunks.
6. **Refresh.** A GitHub Action rebuilds everything nightly, commits `dist/` and `README.md`, and attaches the full node and edge tables plus the galaxy data to the [`data-latest`](https://github.com/h9-tec/model-family-tree/releases/tag/data-latest) release, which the site reads.

### Caveats

- **Declared ancestry only.** 29% of models declare a base. Untagged re-uploads and GGUF conversions without metadata are invisible, so every number is a floor.
- **Activity, not quality.** A base with 30,000 adapters was mostly a tutorial default. Read the finetune-only and 90-day tables alongside the all-time one.
- **Ghost parents.** 4,204 referenced bases are no longer public. They stay in the tree, marked †.
- **Families are heuristic.** Series detection is a regex over names. Fix a wrong grouping by editing `data/families.yaml`.

## Data files

| File | What |
|---|---|
| [`dist/leaderboard.json`](dist/leaderboard.json) | Top 500 models (all time, 90 days, finetune-only), families, organizations |
| [`dist/parents.json`](dist/parents.json) | Every model with descendants, compact columns |
| [`dist/timeseries.json`](dist/timeseries.json) | Monthly new descendants for the top families and models |
| [`dist/children_top.json`](dist/children_top.json) | Top 25 children by downloads for the 3,000 most-descended parents |
| [`dist/llms.txt`](dist/llms.txt) | Plain-text summary for LLMs |
| `data-latest` release | `nodes.parquet` and `edges.parquet`, the full graph |

## Build it yourself

```bash
uv sync
uv run python scripts/build.py all        # downloads the dump (~1.6 GB), builds in about 15 seconds
uv run python scripts/build.py build      # rebuild from the cached dump
uv run pytest
```

## Related

- [Arabic AI Atlas](https://github.com/h9-tec/arabic-ai-atlas): the same idea for one language's ecosystem, with a map.
- Hugging Face shows the tree for one model on its page; this repo aggregates the whole Hub.

## License

Code MIT. Generated data CC BY 4.0, derived from Hub metadata via `cfahlgren1/hub-stats` (Apache-2.0).

*Generated 2026-11-07.*