What is a fine-tuned model?
What is it?
A model is an AI model published by a verified Lab: fine-tune, merge or quantized version. The page describes the model and links to its download.
When to use it
- Find a model suited to a task or your hardware.
- Publish the model your Lab trained (Lab status required).
Page fields
| Type | Fine-tune, merge, quantized or base model. |
|---|---|
| Base model, family, size | Where the model comes from and how many parameters it has. |
| Format and quantization | safetensors, GGUF… and compression level. |
| Training | Datasets and LoRA config used, epochs, date. |
| Hardware | Minimum VRAM, CPU support, speed. |
| Usage and evaluations | Languages, use cases, limits, benchmarks, versions. |
How to use it
“Download the model” button, then the “Use” tab for llama.cpp, Ollama or Transformers commands.