OSS Radar
FareedKhan-dev/kimi-k3-in-c
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU. Why it matters: useful plumbing for shipping LLM-powered features.
GitHub description: A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
Stars
9k
Last 24h
+123est.
Last 7 days
+864est.
Forks
1.5k
Who it's for
Developers, researchers and students who want to run or study a very large model on ordinary hardware, or who want to read a small, portable C99 inference engine. The README is built around memory streaming and the path from checkpoint to generated text.
- Running a 2.78T-parameter model for inference on a laptop-class CPU with 8 GB of RAM
- Studying how large-model inference works, from checkpoint headers through attention and expert routing
- Testing and validating a portable C99 inference engine with no BLAS, framework or GPU dependency
Requirements
From the project README| Operating system | Linux x86-64 (reference); macOS arm64 and Windows x86-64 also build and pass every gate |
|---|---|
| RAM (minimum) | 8 GB |
| RAM (recommended) | Not stated in README |
| GPU required | No |
| VRAM (minimum) | Not stated in README |
| Disk space | 1700 GB |
| Runtime | GCC ≥ 9 or Clang ≥ 10, GNU make or CMake; Python 3.9+ for download, pack and analysis tools |
| Model sizes | 2.78T |
Install
git clone https://github.com/FareedKhan-dev/kimi-k3-in-c.gitWill it run on my machine?
Detecting your browser's hardware hints…
Based only on what the README states. Your choice is saved in this browser and used on every repo page.
Star history (last 1 snapshot)
Only one snapshot so far. The chart fills in as OSS Radar collects daily snapshots.
* / est. Estimated: until we have enough daily snapshots for a repo, its gain is total stars ÷ days since creation. Measured numbers replace estimates automatically.
Maintainer? Add the badge to your README
Shows your live OSS Radar rank and links back here. Updates hourly.
[](https://ossradar.net/repo/FareedKhan-dev/kimi-k3-in-c)<a href="https://ossradar.net/repo/FareedKhan-dev/kimi-k3-in-c"><img src="https://ossradar.net/badge/FareedKhan-dev/kimi-k3-in-c" alt="Trending on OSS Radar"></a>About kimi-k3-in-c
FareedKhan-dev/kimi-k3-in-c is a C project in the LLM tooling category, created 2 months ago. It has 9k GitHub stars and 1.5k forks, and gained +864 stars over the last 7 days (early estimate), ranking #47 of 167 LLM tooling repos tracked by OSS Radar this week.
See more trending LLM tooling repos or the top AI repos this week.
- Language
- C
- Category
- LLM tooling
- Created
- Aug 1, 2026
- Last push
- Oct 2, 2026
- avx2
- c99
- cpu-inference
- deep-learning
- from-scratch
- inference-engine
- kimi-k3
- linear-attention
- llm
- llm-inference
- machine-learning
- memory-efficient
- mixture-of-experts
- moe
- mxfp4
- quantization
- simd
- systems-programming
- transformer
- zero-dependencies
Similar rising repos
- rohitg00/ai-engineering-from-scratch+2.3kest.
Learn AI Engineering! Learn it. Build it. Ship it for others. Why it matters: useful plumbing for shipping LLM-powered features.
- huggingface/transformers+404est.
Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both… Why it matters: useful plumbing for shipping LLM-powered features.
- bojieli/ai-infra-book+864est.
《深入理解 AI Infra：量化分析与系统设计》（李博杰 著）开源书稿：从硬件约束和模型架构出发，量化推导 LLM 推理与训练系统设计。含全书正文、PDF、配套计算工具与实验. Why it matters: useful plumbing for shipping LLM-powered features.
ARIS (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment… Why it matters: useful plumbing for shipping LLM-powered features.
- vllm-project/vllm+489est.
A high-throughput and memory-efficient inference and serving engine for LLMs. Why it matters: useful plumbing for shipping LLM-powered features.
- hiyouga/LlamaFactory+428est.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024). Why it matters: useful plumbing for shipping LLM-powered features.