Skip to content
View BobClawblaw's full-sized avatar
3 followers · 2 following

Achievements

Achievement: Pair Extraordinairex4Achievement: Pull Sharkx3Achievement: Quickdraw

Achievements

Achievement: Pair Extraordinairex4Achievement: Pull Sharkx3Achievement: Quickdraw

Block or report BobClawblaw

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

Pinned Loading

  1. bitcoinmachinecode bitcoinmachinecode Public

    A Bitcoin node, 100% AI-generated: hand-authored x86-64 assembly (NASM) with a C orchestration layer. Fully verifies consensus from genesis; UTXO set MuHash-identical to Bitcoin Core; follows mainn…

    C 3 1

  2. blockyard blockyard Public

    Live monitor, block explorer, markets and 3D block-space viewer for Bitcoin Core. Zero dependencies, self-hosted, read-only. Apache-2.0.

    JavaScript

  3. qwen38-27b-vision-rtx-5090 qwen38-27b-vision-rtx-5090 Public

    Qwen3.8-27B 4-bit + DFlash2 on one RTX 5090, TensorFold native CUDA: image input, the full 262k window in one stream (fp8 KV), 285-309 tok/s short / 126 tok/s at 215k. Against vLLM NVFP4 on the sam…

    Python

  4. glm53-flash-exl3-2x-dgx-sparks glm53-flash-exl3-2x-dgx-sparks Public

    GLM-5.3-Flash EXL3 4 bpw on 2x DGX Spark, TensorFold native (CUDA, TP=2): fused EXL3 prompt kernel at ~1,000 tok/s prefill, DFlash2 drafts, 16 streams, 1M context, kept-state resumes

    Python