Skip to content
View bespokeontology's full-sized avatar
2 followers · 0 following

Block or report bespokeontology

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. frankenpool frankenpool Public

    Pooling frontier LLMs across an NVIDIA RTX 4070 + a 5-year-old M1 MacBook over a $40 Thunderbolt cable. Honest, measured field records — a 70B run across both machines, and a day-old frontier MoE g…

    Python 2 2

  2. openPangu-2.0-Flash-CUDA-ROCm openPangu-2.0-Flash-CUDA-ROCm Public

    openPangu Flash92 — C++/CUDA & C++/HIP ROCm Engines. Fully resident, Blackwell tensor cores, no Python. Powered by openPangu.

    HIP 2

  3. ornith-1.0-9b-critical-review ornith-1.0-9b-critical-review Public

    Same-day field test & critical review of Ornith-1.0-9B agentic coding model on consumer hardware (8GB GPU + 16GB M1). Includes full harness code, artifacts, reproduction steps, and analysis.

    Python 1

  4. the-drivetrain-deficit the-drivetrain-deficit Public

    A Bespoke Ontology systems-analysis report arguing that peak neural-compute specifications fail to predict sustained voice-AI efficiency. Compares Apple’s iOS/A19 Pro architecture with Huawei’s Har…

  5. dragon.c dragon.c Public

    From-scratch C inference engine running Meituan LongCat-Flash-Thinking 560B (FP8 MoE) on a 31GB laptop — 50x measured speed ladder, output-invariant

    C

  6. bespokeontology bespokeontology Public

    bespoke ontology — drivetrain, not engine