Export
llama.cpp
/wiki/llama-cpp
The link always opens the latest version of this page.
Ask an AI about it
Open in ChatGPTA new chat that reads this entry from the site Open in ClaudeThe same, in Claude
Sending this to someone?
MarkdownPlain text for notes apps and AI chats
WordA document to edit and annotate
PDFA4, for printing and sharing
ZIPEverything: the documents, the data, and instructions for AI assistants
Share the link instead of a file, and they will always see the latest version.
Files are a snapshot of today. The live page has anything newer.
growing ·
11 feeds
llama.cpp
Snapshot
Intelligence coverage
llama.cpp is a language model runtime 1 designed to run large language models locally. The project is open source 2 and supports cross-platform deployment 3.
The tool provides GPU acceleration through multiple backends, including CUDA 4, Vulkan 5, and native support for macOS.
Facts 3
| Attribute | Value | Confidence | Sources | Cited |
|---|---|---|---|---|
| Category | language model runtime | low | 1 | 1 |
| Type | offensive disputed
also reported: dual-use (low)
|
low | 1 | source ↗ |
| Open source | yes | low | 1 | 2 |
Platform 4
CUDAmacOSVulkancross-platform
Neighbourhood
Affected by 3
Detected by 4
Detects 1
Frequently mentioned together 16
Sources 66
- Llama.cpp v0.1.0 · Hacker News (YC)
- Kimi K3, and what we can still learn from the pelican benchmark · Hacker News (YC)
- llama.cpp · Hacker News (YC)
- Making Local LLMs Usable on 8GB GPUs · HackerNoon
- My BC-250 Journey (With 40 CUs Unlocked) · Hacker News (YC)
5 of 66 sources shown · Pro unlocks the full list