Skip to content
View EugeneClaw's full-sized avatar
🤖
🤖
0 followers · 8 following
  • Albert Square

Block or report EugeneClaw

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Popular repositories Loading

  1. glm53-flash-apple-silicon glm53-flash-apple-silicon Public

    GLM-5.3-Flash on Apple Silicon (M5 Ultra w/256GB): 2089 tok/s Prefill and 55.2 tok/s decode. Fully Ledgered, all tests and attempts included so that it can be developed further.

    Python 3

  2. local-ai-speed-simulator local-ai-speed-simulator Public

    How fast would AI run on your own hardware? Single-file simulator for local LLM inference — prefill, decode, KV cache, multi-GPU scaling, electricity vs cloud cost.

    HTML

  3. DeepSeek-V4-Flash-3x-DGX-Sparks DeepSeek-V4-Flash-3x-DGX-Sparks Public

    Forked from FlyCockpit/DeepSeek-V4-Flash-3x-DGX-Sparks

    3× NVIDIA DGX Spark runbook for DeepSeek-V4-Flash-0731 — expert parallel + NCCL mesh + DSpark MTP

    Python

  4. DGX-Mac-Prefill-Sim DGX-Mac-Prefill-Sim Public

    Interactive token speed simulator: DGX Spark clusters vs Mac Studio local LLM prefill and decode realtime sim, for a genuine feel of local AI use.

    JavaScript

  5. side-buttons side-buttons Public

    Mouse side buttons (Back/Forward) for macOS - a tribute to (the no longer supported on modern ARM devices) Sensible Side Buttons

    Swift

  6. TensorFold TensorFold Public

    Forked from chadhurley25075-png/TensorFold

    Fast, exact LLM decoding on Apple Silicon (MLX) behind an OpenAI-compatible endpoint

    Python