MoonshotAI/Kimi-K3

This page introduces an external open-source repository. It is not an HDATF product.

What it does

Kimi K3 is an open-weight multimodal Mixture-of-Experts model with 2.8T total and 104B activated parameters and a 1-million-token context window. It understands text, images and video and targets long-horizon coding, knowledge work and reasoning.

How it helps ATF

A model rather than a work tool. Its focus on long coding and knowledge-work sessions could be a loose reference when comparing the models behind executors that Harness hands work to.

License

Custom license Custom or non-standard license. Read the license file before any reuse.

More in this category

• lyogavin/airllm
  AirLLM lowers the GPU memory needed for large language model inference by loading model layers one at a time, so a 70B model can run on a single 4GB GPU without quantization, distillation or pruning. Training support was added too.
• drumih/turbo-fieldfare
  A Swift and Metal runtime that runs Gemma 4 26B-A4B on Apple Silicon Macs in about 2 GB of RAM. It keeps the shared core and KV cache in memory and streams only the needed experts from SSD.
• FareedKhan-dev/kimi-k3-in-c
  A portable C99 engine that runs Kimi K3 inference on one CPU with no GPU, BLAS or framework, streaming the model from disk. The readme reports an 8.24 GB peak memory use, with more RAM only adding speed.
• lidge-jun/opencodex
  opencodex is a local proxy that translates the Codex Responses API into other providers' formats, including streaming and tool calls. It lets Codex, Claude Code, Claude Desktop and Grok Build run models such as Gemini, DeepSeek or Ollama models.
• unslothai/unsloth
  Unsloth is a desktop app for running and training LLM, diffusion, embedding and audio models, including GGUF and MLX formats. Local models can also be used with Claude Code, Codex and MCP, together with web search and RAG.

Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.