GitSeonjeap
English

Sign in

Reading needs no sign-in. Sign in to write posts or comments, or to recommend and report, in the community.

By signing in you agree to the notices below. Community rules · Privacy notice

Keep browsing without signing in

← News

Local AI

Moonshot Releases Open-Weight Model Kimi K3.1 Pro

Posted As of

Moonshot AI has uploaded the weights of Kimi K3.1 Pro, a multimodal agent model, to Hugging Face. The parameter count is listed as 2.8T (official) and the model is under a dedicated license.

What happened

  • The content is based on the Moonshot AI model card on Hugging Face. Reports conflict on the release date, November 4 or 5, so the repository history needs to be checked.
  • The model card describes it as an open-weight native multimodal agent model and Moonshot's top-performing model in the 3T class.
  • It was post-trained with large-scale reinforcement learning on Kimi K3 and is the first model in the K3.1 series.
  • The page lists 2.8T (official) parameters, and the API model ID is kimi-k3.1-pro.
  • The license is not Apache or MIT but a separate "Kimi K3.1 Pro License."

Our take

The official materials include no guidance for running it on laptops or Macs, and reports say it requires a multi-GPU server. We have not found official GGUF or MLX builds, only community uploads. Active parameters, context length, and revenue terms in the license are based on secondary sources and remain unconfirmed, so the LICENSE file should be read directly before any commercial use.

Sources and related posts

More in Local AI

  1. llama.cpp b12200, Qualcomm OpenCL quantization kernel improvements (github.com)

    The llama.cpp b12200 release contains one change that reworks OpenCL q8_0 and small-batch MoE processing. No performance figures were published.

    Local AI| |1 sources |Our take included
  2. llama.cpp b12180 adds text-only Kimi-K3.1-Pro support… Vulkan detects ReBAR (github.com)

    On November 6, llama.cpp build b12180 added text-only Kimi-K3.1-Pro support. The same day, the Vulkan backend began detecting whether ReBAR is supported.

    Local AI| |1 sources
  3. Ollama 0.40.12~0.40.15: LFM3 Expansion, MLX Speculative Decoding and Sampling Improvements (github.com)

    Ollama released four times between October 27 and November 3. LFM3 expanded to Linux and Windows, DFlash speculative decoding became supported on MLX, and top-k sampling got faster.

    Local AI| |1 sources |Our take included

All news