# model-cards

**Repository Path**: mirrors_docker/model-cards

## Basic Information

- **Project Name**: model-cards
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Apache-2.0
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-03-29
- **Last Updated**: 2025-12-27

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# 📦 Docker AI Models Repository

Official model cards and documentation for AI models available on [Docker Hub](https://hub.docker.com/u/ai).

---

## 🚀 Models Overview

### DeepCoder Preview
![DeepCoder Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/agentica-120x-hub@2x.png)

📌 **Description:**  
DeepCoder-14B-Preview is a code reasoning LLM fine-tuned to scale up to long context lengths.

📂 **Model File:** [`ai/deepcoder-preview.md`](ai/deepcoder-preview.md)  
🐳 **Docker Hub:** [`docker.io/ai/deepcoder-preview`](https://hub.docker.com/r/ai/deepcoder-preview)

**Source:**
- https://huggingface.co/agentica-org/DeepCoder-14B-Preview

---

### DeepSeek R1 Distill LLaMA
![DeepSeek Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/deepseek-120x-hub@2x.svg)

📌 **Description:**  
Distilled LLaMA by DeepSeek, fast and optimized for real-world tasks.

📂 **Model File:** [`ai/deepseek-r1-distill-llama.md`](ai/deepseek-r1-distill-llama.md)  
🐳 **Docker Hub:** [`docker.io/ai/deepseek-r1-distill-llama`](https://hub.docker.com/r/ai/deepseek-r1-distill-llama)

**Sources:**
- https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B
- https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B

---

### Devstral Small 1.1
![Mistral Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/mistral-120x-hub@2x.svg)

📌 **Description:**  
Devstral Small 1.1 is an agentic coding LLM (24B) fine-tuned from Mistral-Small-3.1 with a 128K context window.

📂 **Model File:** [`ai/devstral-small.md`](ai/devstral-small.md)  
🐳 **Docker Hub:** [`docker.io/ai/devstral-small`](https://hub.docker.com/r/ai/devstral-small)

---

### Gemma 3
![Gemma Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/gemma-120x-hub@2x.svg)

📌 **Description:**  
Google's latest Gemma, small yet strong for chat and generation.

📂 **Model File:** [`ai/gemma3.md`](ai/gemma3.md)  
🐳 **Docker Hub:** [`docker.io/ai/gemma3`](https://hub.docker.com/r/ai/gemma3)

**Source:**
- https://huggingface.co/google/gemma-3-4b-it

---

### Gemma 3 QAT
![Gemma Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/gemma-120x-hub@2x.svg)

📌 **Description:**  
Google's latest Gemma, in its QAT (quantization aware trained) variant.

📂 **Model File:** [`ai/gemma3-qat.md`](ai/gemma3-qat.md)  
🐳 **Docker Hub:** [`docker.io/ai/gemma3-qat`](https://hub.docker.com/r/ai/gemma3-qat)

---

### Gemma 3N
![Gemma Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/gemma-120x-hub@2x.svg)

📌 **Description:**  
Efficient multimodal AI for text, image, audio, and video on low-resource devices.

📂 **Model File:** [`ai/gemma3n.md`](ai/gemma3n.md)  
🐳 **Docker Hub:** [`docker.io/ai/gemma3n`](https://hub.docker.com/r/ai/gemma3n)

---

### GPT-OSS
![OpenAI Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/openai-120x-hub.svg)

📌 **Description:**  
OpenAI's open-weight models designed for powerful reasoning, agentic tasks.

📂 **Model File:** [`ai/gpt-oss.md`](ai/gpt-oss.md)  
🐳 **Docker Hub:** [`docker.io/ai/gpt-oss`](https://hub.docker.com/r/ai/gpt-oss)

---

### Granite Embedding Multilingual
![IBM Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/ibm-120x-hub.svg)

📌 **Description:**  
Granite Embedding Multilingual is a 278 million parameter, encoder‑only XLM‑RoBERTa‑style model.

📂 **Model File:** [`ai/granite-embedding-multilingual.md`](ai/granite-embedding-multilingual.md)  
🐳 **Docker Hub:** [`docker.io/ai/granite-embedding-multilingual`](https://hub.docker.com/r/ai/granite-embedding-multilingual)

---

### Granite 4.0 Micro
![IBM Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/ibm-120x-hub.svg)
📌 **Description:**
3B long-context instruct model with RL alignment, IF, tool use, and enterprise optimization.

📂 **Model File:** [`ai/granite-4.0-micro.md`](ai/granite-4.0-micro.md)
🐳 **Docker Hub:** [`docker.io/ai/granite-4.0-micro`](https://hub.docker.com/r/ai/granite-4.0-micro)

---

### Granite 4.0 H Micro
![IBM Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/ibm-120x-hub.svg)
📌 **Description:**
3B long-context instruct model with RL alignment, IF, tool calling, and enterprise readiness.

📂 **Model File:** [`ai/granite-4.0-h-micro.md`](ai/granite-4.0-h-micro.md)
🐳 **Docker Hub:** [`docker.io/ai/granite-4.0-h-micro`](https://hub.docker.com/r/ai/granite-4.0-h-micro)

---

### Granite 4.0 H Tiny
![IBM Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/ibm-120x-hub.svg)
📌 **Description:**
7B long-context instruct model with RL alignment, IF, tool use, and enterprise optimization.

📂 **Model File:** [`ai/granite-4.0-h-tiny.md`](ai/granite-4.0-h-tiny.md)
🐳 **Docker Hub:** [`docker.io/ai/granite-4.0-h-tiny`](https://hub.docker.com/r/ai/granite-4.0-h-tiny)

---

### Granite 4.0 H Small
![IBM Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/ibm-120x-hub.svg)
📌 **Description:**
32B long-context instruct model with RL alignment, IF, tool use, and enterprise optimization.

📂 **Model File:** [`ai/granite-4.0-h-small.md`](ai/granite-4.0-h-small.md)
🐳 **Docker Hub:** [`docker.io/ai/granite-4.0-h-small`](https://hub.docker.com/r/ai/granite-4.0-h-small)

### Llama 3.1
![Meta Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/meta-120x-hub@2x.svg)

📌 **Description:**  
Meta's LLaMA 3.1: Chat-focused, benchmark-strong, multilingual-ready.

📂 **Model File:** [`ai/llama3.1.md`](ai/llama3.1.md)  
🐳 **Docker Hub:** [`docker.io/ai/llama3.1`](https://hub.docker.com/r/ai/llama3.1)

**Source:**
- https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct

---

### Llama 3.2
![Meta Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/meta-120x-hub@2x.svg)

📌 **Description:**  
Solid LLaMA 3 update, reliable for coding, chat, and Q&A tasks.

📂 **Model File:** [`ai/llama3.2.md`](ai/llama3.2.md)  
🐳 **Docker Hub:** [`docker.io/ai/llama3.2`](https://hub.docker.com/r/ai/llama3.2)

**Sources:**
- https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct
- https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct

---

### Llama 3.3
![Meta Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/meta-120x-hub@2x.svg)

📌 **Description:**  
Newest LLaMA 3 release with improved reasoning and generation quality.

📂 **Model File:** [`ai/llama3.3.md`](ai/llama3.3.md)  
🐳 **Docker Hub:** [`docker.io/ai/llama3.3`](https://hub.docker.com/r/ai/llama3.3)

---

### Magistral Small 3.2
![Mistral Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/mistral-120x-hub@2x.svg)

📌 **Description:**  
24B multimodal instruction model by Mistral AI, tuned for accuracy, tool use & fewer repeats.

📂 **Model File:** [`ai/magistral-small-3.2.md`](ai/magistral-small-2506.md)  
🐳 **Docker Hub:** [`docker.io/ai/magistral-small-3.2`](https://hub.docker.com/r/ai/magistral-small-2506)

---

### Mistral
![Mistral Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/mistral-120x-hub@2x.svg)

📌 **Description:**  
Efficient open model with top-tier performance and fast inference.

📂 **Model File:** [`ai/mistral.md`](ai/mistral.md)  
🐳 **Docker Hub:** [`docker.io/ai/mistral`](https://hub.docker.com/r/ai/mistral)

**Source:**
- https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3

---

### Mistral Nemo
![Mistral Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/mistral-120x-hub@2x.svg)

📌 **Description:**  
Mistral fine-tuned via NVIDIA NeMo for smoother enterprise use.

📂 **Model File:** [`ai/mistral-nemo.md`](ai/mistral-nemo.md)  
🐳 **Docker Hub:** [`docker.io/ai/mistral-nemo`](https://hub.docker.com/r/ai/mistral-nemo)

**Source:**
- https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407

---

### mxbai-embed-large
![Mixedbread Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/mixedbread-120x-hub@2x.svg)

📌 **Description:**  
mxbai-embed-large-v1 is a top English embed model by Mixedbread AI, great for RAG and more.

📂 **Model File:** [`ai/mxbai-embed-large.md`](ai/mxbai-embed-large.md)  
🐳 **Docker Hub:** [`docker.io/ai/mxbai-embed-large`](https://hub.docker.com/r/ai/mxbai-embed-large)

**Source:**
- https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1

---

### Nomic Embed Text v1.5
![Nomic Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/nomic-120x-hub.svg)

📌 **Description:**  
Nomic Embed Text v1 is an open‑source, fully auditable text embedding model.

📂 **Model File:** [`ai/nomic-embed-text-v1.5.md`](ai/nomic-embed-text-v1.5.md)  
🐳 **Docker Hub:** [`docker.io/ai/nomic-embed-text-v1.5`](https://hub.docker.com/r/ai/nomic-embed-text-v1.5)

---

### Phi-4
![Microsoft Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/phi-120x-hub@2x.svg)

📌 **Description:**  
Microsoft's compact model, surprisingly capable at reasoning and code.

📂 **Model File:** [`ai/phi4.md`](ai/phi4.md)  
🐳 **Docker Hub:** [`docker.io/ai/phi4`](https://hub.docker.com/r/ai/phi4)

**Source:**
- https://huggingface.co/microsoft/phi-4

---

### Qwen 2.5
![Qwen Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/qwen-120x-hub@2x.svg)

📌 **Description:**  
Versatile Qwen update with better language skills and wider support.

📂 **Model File:** [`ai/qwen2.5.md`](ai/qwen2.5.md)  
🐳 **Docker Hub:** [`docker.io/ai/qwen2.5`](https://hub.docker.com/r/ai/qwen2.5)

**Source:**
- https://huggingface.co/Qwen/Qwen2.5-7B-Instruct

---

### Qwen 3
![Qwen Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/qwen-120x-hub@2x.svg)

📌 **Description:**  
Qwen3 is the latest Qwen LLM, built for top-tier coding, math, reasoning, and language tasks.

📂 **Model File:** [`ai/qwen3.md`](ai/qwen3.md)  
🐳 **Docker Hub:** [`docker.io/ai/qwen3`](https://hub.docker.com/r/ai/qwen3)

---

### Qwen 3 Coder
![Qwen Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/qwen-120x-hub@2x.svg)

📌 **Description:**  
Qwen3-Coder is Qwen's new series of coding agent models.

📂 **Model File:** [`ai/qwen3-coder.md`](ai/qwen3-coder.md)  
🐳 **Docker Hub:** [`docker.io/ai/qwen3-coder`](https://hub.docker.com/r/ai/qwen3-coder)

---

### QwQ
![Qwen Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/qwen-120x-hub@2x.svg)

📌 **Description:**  
Experimental Qwen variant—lean, fast, and a bit mysterious.

📂 **Model File:** [`ai/qwq.md`](ai/qwq.md)  
🐳 **Docker Hub:** [`docker.io/ai/qwq`](https://hub.docker.com/r/ai/qwq)

**Source:**
- https://huggingface.co/Qwen/QwQ-32B

---

### Seed OSS
![ByteDance Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/byte-seed-120x.svg)

📌 **Description:**  
Designed for reasoning, agent and general capabilities, and versatile developer-friendly features.

📂 **Model File:** [`ai/seed-oss.md`](ai/seed-oss.md)  
🐳 **Docker Hub:** [`docker.io/ai/seed-oss`](https://hub.docker.com/r/ai/seed-oss)

---

### SmolLM 2
![Huggingface Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/hugginfface-120x-hub@2x.svg)

📌 **Description:**  
Tiny LLM built for speed, edge devices, and local development.

📂 **Model File:** [`ai/smollm2.md`](ai/smollm2.md)  
🐳 **Docker Hub:** [`docker.io/ai/smollm2`](https://hub.docker.com/r/ai/smollm2)

**Sources:**
- https://huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct
- https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct

---

### SmolLM 3
![Huggingface Logo](https://github.com/docker/model-cards/raw/refs/heads/main/logos/hugginfface-120x-hub@2x.svg)

📌 **Description:**  
SmolLM3 is a 3.1B model for efficient on-device use, with strong performance in chat.

📂 **Model File:** [`ai/smollm3.md`](ai/smollm3.md)  
🐳 **Docker Hub:** [`docker.io/ai/smollm3`](https://hub.docker.com/r/ai/smollm3)


## 🛠️ Tools

### Model Cards CLI

A command-line tool for working with model cards. See [tools/model-cards-cli/README.md](tools/model-cards-cli/README.md) for details.

Key features:
- Update "Available model variants" tables in model card markdown files
- Inspect model repositories to extract metadata
- Upload model overviews to Docker Hub
- Support for custom namespaces and private repositories

## 📝 Contributing

To add or update model cards:
1. Create/edit the markdown file in the `ai/` directory
2. Use the Model Cards CLI to update variant tables
3. Submit a pull request

## 📄 License

See [LICENSE](LICENSE) file for details.