---
title: "Discussion on \"Building llamini.cpp: a from-scratch llama.cpp core in C99, zero dependencies\" | Hashnode"
description: "Discussion on \"Building llamini.cpp: a from-scratch llama.cpp core in C99, zero dependencies\". At a glance\n\n\n\n\n\n\n\n\nDialect\nPure C99 (POSIX + libc) — 0 third-party dependencies\n\n\nBuild\nOne command: make → llamini\n\n\nModels\nTinyLlama 1.1B, Qwen2.5 0.5B, GPT-2 124M, Gemma 2B\n\n\nQuants\nQ4_K, Q6_K, Q5"
url: "https://hashnode.com/posts/building-llamini-cpp-a-from-scratch-llama-cpp-core-in-c99-zero-dependencies/6a9f17866f526dd1c8ea4868"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Building llamini.cpp: a from-scratch llama.cpp core in C99, zero dependencies](https://mhosm.hashnode.dev/building-llamini-cpp-a-from-scratch-llama-cpp-core-in-c99-zero-dependencies?utm_source=hashnode&utm_medium=feed)

At a glance Dialect Pure C99 (POSIX + libc) — 0 third-party dependencies Build One command: make → llamini Models TinyLlama 1.1B, Qwen2.5 0.5B, GPT-2 124M, Gemma 2B Quants Q4\_K, Q6\_K, Q5

Sep 7 · 26 min read · mhosm.hashnode.dev  
Read the article

-   [#llamacpp](https://hashnode.com/tag/llamacpp)
-   [#llama-cpp](https://hashnode.com/tag/llama-cpp)
-   [#cpu-optimization](https://hashnode.com/tag/cpu-optimization)

## Written by

[Mohammad Hatif Osmani](https://hashnode.com/@mhosm)

@mhosm

  
[View profile](https://hashnode.com/@mhosm)

Web Developer · Machine Learning Engineer · Open Source Contributor

A passionate software developer who loves experimenting and learning new tech.

## Responses

Markdown supported · ⌘↵ to post

No responses yet.