Skip to content

[Request] Apple Silicon / MLX / EXO support roadmap #5

Description

@zhwangsir

Request: Apple Silicon / MLX / EXO support roadmap for Kimi K3

First of all, thank you for open-sourcing Kimi K3 — the 32B/1T MoE design and the reported benchmarks are very impressive.

Hardware context

I operate a 4× Mac Studio M3 Ultra cluster, each with 512 GB unified memory, connected via RDMA over Thunderbolt. This gives ~2 TB of shared addressable memory and very high inter-node bandwidth, which seems ideal for running Kimi K3 in a distributed setting.

Current situation

The current first-party inference integrations focus on NVIDIA/AMD stacks (vLLM, SGLang, TokenSpeed). For Apple Silicon, the viable paths appear to be:

  • MLX (via mlx-lm or mlx-community conversion)
  • EXO (distributed Apple Silicon inference with RDMA support)

Both would need support for the new architecture components introduced in Kimi K3:

  • Kimi Delta Attention (KDA)
  • Attention Residuals
  • Stable LatentMoE
  • MoonViT-V2 (for multimodal)
  • MXFP4 / MXFP8 weight handling

Questions

  1. Does Moonshot AI plan to release reference implementations or conversion scripts for MLX / Apple Silicon?
  2. Is there a target timeline for community ports (e.g., llama.cpp, EXO, mlx-community)?
  3. Would the team consider releasing BF16/FP16 weights in addition to MXFP4/8 to lower the barrier for frameworks that do not yet support these new FP4/FP8 layouts?
  4. Are there detailed architecture docs or reference CUDA kernels coming that would help third-party implementations?

I am happy to contribute validation resources (remote access to the 4-node M3 Ultra RDMA cluster, benchmarks, profiling) if that helps an Apple Silicon port move faster.

References

Thank you again for the open-source release.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions