Local AI Explorer
Run locally
Describe the machine — memory, number of devices, platform, quantization, context, batch — and the atlas lists the downloadable models estimated to fit, with the breakdown behind each number and the GGUF / MLX artifacts recorded for them. Estimates, never measurements.
Describe a machine to start
Try 64 GB · 4-bit, 2 × 24 GB · 8-bit · NVIDIA, 128 GB · 4-bit · 128K · coding — or start from a device on /hardware.