ByteSized: a 3KB LLM inference engine in pure C
A 3,156-byte C engine that runs SmolLM2-135M token-for-token identical to Hugging Face, with no dependencies, aimed at embedded and resource-constrained devices.
Why it matters
Whole LLM inference in 3KB of C: the smallest self-contained engine yet, a teaching artifact and a proof that tiny models can run anywhere.
What you could build with it
An embedded developer could port ByteSized to a microcontroller to run a tiny assistant offline on a device with almost no memory.
Does it hold up?
Too early to judge: launched Nov 3 with a handful of stars and one demo model. The engine is a minimal proof of concept, not a deployment tool yet.
Built with ByteSized
- ByteSized: 3KB LLM Inference Engine in C Launches Todayemergent.sh · Launch coverage: pure C, no dynamic allocation, 4-bit and 8-bit quantized models, built for embedded systems.
Learn more
First spotted on github: source.
More AI models
VoiceStudio: open-source, fully-local ElevenLabs alternative for voice cloning, dubbing, and audiobooksdebpalash/VoiceStudio is a desktop app that runs voice cloning, voice design, video dubbing, dictation, transcription…models · JEV 0.75Soup: fine-tune an 8B LLM on a 4 GB laptop GPU from one YAML fileAn open-source CLI that fine-tunes LLMs from a single YAML file, with layer streaming that trains an 8B model on a 4…models · JEV 0.73Tencent Hunyuan Hy3: open 295B MoE with 21B active under Apache 2.0Tencent open-sourced Hy3, a 295B-parameter mixture-of-experts model with only 21B parameters active per token, under…models · JEV 0.73NVIDIA Isaac Lab 3.0 GA + Isaac OS open runtime + Agile ONE SN humanoidMajor Isaac platform expansion at GTC Berlin Oct 21: Isaac Lab 3.0 is generally available as the open-source robot…models · JEV 0.73NVIDIA Nemotron 3.5 Retriever collection: Embed 8B/1B, Rerank 8B, Parse 631MNVIDIA's Oct 21 collection drop for agentic retrieval: Nemotron-3.5-Embed in 8B BF16, 1B BF16 and 1B NVFP4…models · JEV 0.72Kimi K3.1 Pro: Moonshot's 2.8T open-weight flagship officially launchesMoonshot AI officially launched Kimi K3.1 Pro on Oct 23, a mixture-of-experts model with 2.8 trillion total / 104…models · JEV 0.72
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.