kimi-k3-in-c
A portable C99 inference engine for running Kimi K3 on a CPU without a GPU or machine-learning framework. It streams the large checkpoint from disk to support inference with limited RAM, for batch text generation or text chat.
Pick a small issue you can reproduce, then fix it with your AI coding agent.
Share on XLicense: Apache-2.0
Overview
kimi-k3-in-c is a portable C99 inference engine for running the Kimi K3 language model without BLAS, a machine-learning framework, or a GPU. It addresses the memory demands of a 1.56 TB checkpoint by streaming model data from disk; the README reports peak memory use of 8.24 GB. More RAM can reduce disk waiting. Run it with the model and tokenizer files for batch text generation or text-only XTML chat. Incremental generation carries state between tokens.
Key features
- Streams model data from disk to run with limited RAM.
- Generates text from prompts with configurable token limits and stop IDs.
- Incremental mode carries the KV cache and recurrent state between generated tokens.
- Supports text-only XTML chat with multi-turn history.
Best for
Useful for developers experimenting with Kimi K3 inference on CPU-only machines or systems with limited RAM. Expect generation to be slow when the model must be read from disk.
- Upstream
- FareedKhan-dev/kimi-k3-in-c
- Fork on GitHub
- Guo-astro/kimi-k3-in-c
- Upstream stars
- 11k
- Category
- AI agents and LLM tools
- License
- Apache-2.0
- Forked
- 2026-10-21
- Sync status
- In syncLast synced 2026-11-11
More in AI agents and LLM tools
/last30days is an AI-agent skill for researching recent discussions across social platforms, video, news, markets, and the web. It brings scattered signals together in a synthesized brief for trend research and preparation.
Forked 2026-10-22Last synced 2026-11-11License: MITAI agents and LLM toolsGitHub
LayerFS gives AI agents writable workspaces over shared history, so they can work in parallel without copying the base. Use it to checkpoint, branch, rewind, and merge agent changes.
Forked 2026-10-21Last synced 2026-11-11License: MITAI agents and LLM toolsGitHub
Magnitude runs open models locally and tunes kernels for your hardware. Use it to connect local models to supported agents or an OpenAI-compatible client.
Forked 2026-10-19Last synced 2026-11-11License: Apache-2.0AI agents and LLM toolsGitHub
A collection of AI research skills and guides that helps researchers with idea evaluation, literature research, paper writing, and pre-submission review.
Forked 2026-10-18Last synced 2026-11-11Custom license (see repository)AI agents and LLM toolsGitHub