Local AI models FLE Link runs in one command
FLE Link reads your machine, installs the engine that fits and downloads the model. These are the models of the built-in catalog and recipes; any other GGUF file works with flelink run /path/to/model.gguf.
- DeepSeek V4.1 Flash 763B mixture of experts, 232 GiB; 763B, hot half on the GPU
- Qwen3.8-Flash-Next 125B mixture of experts, 88.9 GB
- Katy 27B dense 27B with a draft model
- Kate 27B Katy without the refusal direction
- Llama 3.2 1B 1B, a first try on any laptop
Not sure what fits? Start from your card →
Install FLE Link
curl -fsSL https://flelink.run/install.sh | shWindows: irm https://flelink.run/install.ps1 | iex. Open source, MIT. No account, no telemetry. What FLE Link does →