1.4 Model Landscape
AI-generated content may contain errors. Always verify against official sources.
1.4 Model Landscape
Key Concepts: Closed models · Open-weight models · Size trade-offs · Choosing the right model
Official Sources: OpenAI Models · Anthropic Models · Hugging Face Model Hub
Closed / Proprietary Models
These are hosted by providers — you access them via API. You cannot run them locally or inspect their weights.
| Model Family | Provider | Strengths |
|---|---|---|
| GPT-4o / o3 | OpenAI | General reasoning, multimodal, tool use |
| Claude 3.x / 3.5 | Anthropic | Long-context, coding, safety-focused |
| Gemini 1.5 / 2.0 | Very large context windows, multimodal |
Always check the provider's official docs for the latest available models and context windows — these change frequently.
Open-Weight Models
These models have publicly available weights. You can run them locally, fine-tune them, and deploy them on your own infrastructure.
| Model Family | Provider | License |
|---|---|---|
| LLaMA 3.x | Meta | Meta Community License |
| Mistral / Mixtral | Mistral AI | Apache 2.0 |
| DeepSeek | DeepSeek | MIT |
| Qwen 2.5 | Alibaba | Apache 2.0 |
| Phi-3 / Phi-4 | Microsoft | MIT |
| Gemma 2 | Gemma Terms |
Closed vs Open — How to Choose
┌──────────────────────────────────────────────┐
│ Use Closed Models when: │
│ • Highest quality output needed │
│ • Fast time-to-market matters │
│ • Multimodal input required │
├──────────────────────────────────────────────┤
│ Use Open Models when: │
│ • Data privacy / on-premise required │
│ • Fine-tuning on your own data needed │
│ • High-volume inference cost control │
│ • Offline / edge deployment │
└──────────────────────────────────────────────┘
Model Size & Hardware
| Size | VRAM needed (fp16) | Notes |
|---|---|---|
| 7B | ~14 GB | Single consumer GPU |
| 13B | ~26 GB | Single professional GPU |
| 70B | ~140 GB | Multi-GPU or quantised |
| 400B+ | 800 GB+ | Multi-node cluster |
4-bit quantisation (GGUF/AWQ/GPTQ) reduces VRAM by approximately 4× compared to fp16, with a modest quality trade-off. A 70B model in 4-bit (~35 GB) can fit on 2× consumer GPUs.
Further Reading
- 📘 OpenAI Model Overview
- 📘 Anthropic Model Overview
- 📘 Hugging Face Model Hub
- 🏆 LMSYS Chatbot Arena Leaderboard
Next → 1.5 Running Your First LLM