Compare Models
Side-by-side comparison foundation. Select multiple models and evaluate hardware fit.
| Model | Size | Min VRAM | Context | Use Cases |
|---|---|---|---|---|
| Llama 3.1 8B | 8B | 6GB | 128,000 | chat, general, instruction-following, rag |
| Llama 3.1 70B | 70B | 40GB | 128,000 | advanced-reasoning, agent, analysis, multilingual |
| Mistral 7B | 7B | 5GB | 32,000 | chat, instruction-following, function-calling |
| Mistral NeMo 12B | 12B | 8GB | 128,000 | chat, coding, reasoning, long-context |
| DeepSeek Coder 6.7B | 6.7B | 5GB | 16,000 | coding, code-review, code-completion |
| DeepSeek Coder 33B | 33B | 22GB | 16,000 | coding, repository-analysis, test-generation |
| Phi-3 Mini | 3.8B | 3GB | 4,000 | edge, chat, reasoning, low-latency |
| Phi-3 Medium | 14B | 10GB | 128,000 | reasoning, chat, analysis |