Open-source engines run Kimi K3 on low-end devices

Recent open-source engines like WASTE enable running the 2.78T-parameter Kimi K3 on consumer devices via innovative weight-loading mechanisms, breaking the traditional memory barrier.

Confirmed

WASTE engine: Developer Marco Bambini released WASTE (Weight-Aware Streaming Tensor Engine), a dependency-free C inference engine that runs the unmodified Kimi K3 in 29GB RAM, achieving 0.5 TPS on a consumer laptop.
Core mechanism: Streams weights directly from NVMe when RAM is insufficient. @机器之心 tested on a 128GB unified-memory Mac, successfully loading 1.56TB of official MXFP4 weights via streaming, with very slow generation but functional responses.
C99 minimal inference: A developer wrote a minimal C99 engine for Kimi K3, leveraging 93% on-demand parameters, running on a single CPU with 8.24GB RAM.

Why it matters

Lower deployment barrier: These projects show that software optimizations can bypass expensive hardware limits, allowing individuals to run massive models on ordinary laptops or old devices, promoting local AI adoption.

2026-08-01 ~ 2026-08-03 · 7 related posts

Full story(3 episodes)→

Episode 1: Moonshot's Open-Source Kimi K3 Lands on Multiple Platforms(2026-08-01, 4 posts)
Episode 2: Open-source engines run Kimi K3 on low-end devices(2026-08-01, 7 posts)
Episode 3: Kimi K3 Runs on Single CPU with 8GB RAM via Pure C(2026-08-03, 3 posts)

Primary sources

Bypassing RAM Limits: Open-Source C Engine Runs 2.78T Kimi K3 Locally — ab2377 · 2026-08-03 08:16 (UTC+08:00)
Full 2.78T-parameter Kimi K3 Runs on Consumer Laptop via NVMe Streaming — rickasaurus · 2026-08-01 11:27 (UTC+08:00)
Running 1.6TB Kimi K3 Weights: 128GB Mac vs 80x RTX 5090 Cluster — 机器之心 · 2026-08-01 11:38 (UTC+08:00)

[source] Full 2.78T-parameter Kimi K3 Runs on Consumer Laptop via NVMe Streaming — rickasaurus · 2026-08-01
[source] Running 1.6TB Kimi K3 Weights: 128GB Mac vs 80x RTX 5090 Cluster — 机器之心 · 2026-08-01
Open-Source Engine 'Waste' Runs Kimi K3 on Just 29GB of RAM — galapag0 · 2026-08-01
Run 2.78T-Parameter Kimi K3 on a Laptop: WASTE Engine Achieves 0.5 TPS — zainhas · 2026-08-01
Running Kimi K3 in Pure C99: Low-Config Inference on 8GB RAM — FareedKhan557 · 2026-08-02
[source] Bypassing RAM Limits: Open-Source C Engine Runs 2.78T Kimi K3 Locally — ab2377 · 2026-08-03
Running 2.78T Parameter Kimi K3 on a Single CPU with 8GB RAM — Saboo_Shubham_ · 2026-08-03