Category
Local & Private AI
Run it on your own machine. No cloud, no telemetry, no one reading over your shoulder.
10 verified projects
Local AIOpen · Apache-2.0
Bonsai 27B
A 27B model pruned down to 3.9GB — small enough to live in your pocket
★ ~34k HF downloads/mo on the 1-bit MLX build aloneearly
Local AIOpen · Apache-2.0
Colibri
A 744B-parameter model on a 25GB laptop, in pure C
★ 14.8kexperimental
Local AIOpen · Apache-2.0
exo
Your spare Macs, united into one AI cluster
★ 45kmaintained
Local AIOpen · Apache-2.0
Jan
The open answer to LM Studio
★ 43.6kmaintained
Local AIOpen · Apache-2.0
llamafile
A whole chatbot in one portable file
★ 25.4kmaintained
Local AIOpen · MIT
Maple Preview
A 20B ternary MoE in 5.31GB, doing 218 tok/s on a Mac mini
★ ~275 HF likes, ~1.1k downloads in week oneearly
Local AIOpen · MIT
mistral.rs
Multimodal inference in one Rust binary
★ 7.2kmaintained
Local AIOpen · Apache-2.0
Muse Glimmer 30B
Meta's return to open weights skips the Llama license entirely — clean Apache-2.0, on-device agents
★ 1.63k HF likes, ~293k downloads/mo across the BF16, quantized, GGUF, and ExecuTorch reposearly
Local AIOpen · MIT
Ollama
The one-liner that made local AI normal
★ 175kmaintained
Local AIOpen · MIT
OmniRoute
One endpoint, 231 providers, zero loyalty
★ 18.7kmaintained
Keep exploring