llamafile
Distribute and run LLMs with a single file.
Local inference
Open llamafile in AirStackWhat llamafile’s own pages say
| What it says it does | Distribute and run LLMs with a single file. github.com |
|---|---|
| Platforms | BSD, Linux, macOS, Windows github.com |
| Deployment | locally github.com |
| Integrations | Cosmopolitan Libc, llama.cpp, whisper.cpp github.com |
| Open source | Yes github.com |
| License | While the llamafile project is Apache 2.0-licensed, github.com |
| Models supported | Qwen3.5 0.8B, GGUF github.com |
Each value is a quote AirStack found on the product’s own pages, read 2026-11-04. A missing field means AirStack has not found it on its pages.