Curated by
More in GitHub repos to check out
See all 34 →LinkedIn Engine Template for Development
github.com
AI Agent Skill for Researching Topics Across Platforms
github.com
Unofficial Python API for Google NotebookLM
github.com
More from Stacklist Team
See all stacks →Sleigh the Holidays: Top Gift Ideas!
8 cards
Must-See Video Content Trends
5 cards
Running Essentials for Beginners
7 cards · Sports
Camelid: Rust-native Local Inference Backend
Camelid is a Rust-native local LLM inference engine that loads GGUF models and serves them via an OpenAI-style API with reproducible evidence and token-for-token parity guarantees. It ships as a single static binary with built-in tokenizer, GGUF loader, CPU kernels, and Metal GPU support, plus a web UI and terminal chat interface.
Built for AI agentsACO · 7245 tokens
Summary
Camelid is a Rust-native local LLM inference engine that loads GGUF models and serves them via an OpenAI-style API with reproducible evidence and token-for-token parity guarantees. It ships as a single static binary with built-in tokenizer, GGUF loader, CPU kernels, and Metal GPU support, plus a web UI and terminal chat interface.
Tags
llm-inference · rust · local-ai · gguf · openai-api · gpu-acceleration · terminal-ui
Key entities
Camelid (technology, 0.99) · Rust (technology, 0.98) · GGUF (technology, 0.98) · OpenAI API (technology, 0.95) · Metal GPU (technology, 0.92) · Ollama (technology, 0.85) · llama.cpp (technology, 0.85) · Llama-3.2 (technology, 0.9) · TinyLlama (technology, 0.88) · Gemma 4 (technology, 0.85) · token-for-token parity (concept, 0.92) · reproducible evidence (concept, 0.9)
Classification
reference · language en · status final
Provenance
claude-haiku-4-5 via @stacklist/be@0.1.0, confidence 0.85, 17 Jun 2026