Skip to content
View HenryNdubuaku's full-sized avatar
  • Cactus Compute
  • London
  • 04:17 (UTC)

Block or report HenryNdubuaku

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.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
HenryNdubuaku/README.md

Henry Ndubuaku

LinkedIn Twitter Email Spotify

I could train a 1B-A200m model on an iPhone 17 Pro at ~650 tokens/sec. It will take 360 days on 20B tokens of training data and use 156KW of electricity which cost $51. The phone will fry of course, so I wrote algorithms to run inference on your phone rather. We named it after a plant that survives in resource-constrained environments, the Cactus.

cactus can run similar model on your Grandma’s Pixel 6a at 80 tokens/second while only draining 10% battery per hour of continuous inference and using 250MB RAM only. YCombinator & Oxford's Seed Fund gave us first checks in July 2025, and we released Cactus v1 in Sep 2025.

Ofc, we took even more money from FCVC (portfolio include Slack, Coinbase, GitLab, Instacart etc.), and 6 smaller funds like Transpose (run by Garry Tan's brother). Besides VCs, Cactus also received checks from fellow YC founders, as well as 62 tech CTOs/VP/Directors both via syndicate and directly at Google DeepMind etc.

We have now grown to 4.4k GitHub stars, power cool products you've probably heard of. 6 exceptionally gifted Research Engineers from UCLA, Nokia, Google, Stanford, Oxford have joined us! The project is also co-maintained by groups at UCLA, Yale, Upenn, Imperial, Georgia, NUS, UCI, CU Boulder and UCI.

I always dreamt of joining DeepMind, Waymo or Nvidia, even had an offer from one of those. But I might be up to something here, who knows? I want Cactus to hit $1m MRR this year, but I might legit be a crazy person...pending official diagnosis.

Core Expertise

Maths Computing AI/ML/RL Distributed Systems GPU

Main Tools

Python C++ PyTorch Jax CUDA Vulkan Neon Cloud

Career Progression

  • 2025-XX: Cactus (YC S25) - Founder & CTO (tiny inference engine for phones and wearables).
  • 2024-25: Deep Render - AI Research Engineer (realtime video models that run on phone GPU/NPU).
  • 2021-24: Wisdm - ML Software Engineer (distributed perception AI for Maxar Defence satelite views).
  • 2019-21: MSc + Open-source activities (JAX/NanoDl, Torch/SuperLazyAutograd, CUDARepo, etc.).
  • 2018-19: Google GADS Scholarship Programme with Andela (pre-MSc), around systems design.
  • 2017-18: National Youth service, posted to software engineering after bootcamp, mostly ARM.
  • 2012-16: Started uni at 15y, covered EECS, data structures, algorithms, maths, physics.

Fun Highlights

  • Wrote Maths, CS & AI Compendium, a veeery unconventional textbook.
  • Kevin Murphy (DeepMind Principal), Thomas Wolf (HuggingFace Co-foubder), Daniel Holtz (Mid Journey Founder), Steve Messina (IBM CTO) followed back on X.
  • After CUDARepo, Nvidia reached out, I did 7 technical rounds, got a verbal offer, back-and-forth over YOE/pay, then I got YC.
  • Did MSc at QMUL, just to work with Prof Matt Purver (Ex-Stanford Researcher on CALO), did my project/thesis with his team.
  • Did BEng under Prof Onyema Uzoamaka (Rumoured first Nigerian CS grad from MIT), he taught computing archs off-head!

Personal Life

  • Profile: Nigerian, 30y, 185m, 83kg, Capricorn & speak Igbo fluently
  • Hobbies: calisthenics, UFC, chess, music, dance
  • Music: Tyler The Creator, RAYE, Mk,Gee, Jacob Collier, Dominic Fike
  • Philosophy: Humanist Christian, unpolitical

Pinned Loading

  1. cactus-compute/cactus cactus-compute/cactus Public

    Low-latency AI engine for mobile devices & wearables

    C 4.4k 325

  2. maths-cs-ai-compendium maths-cs-ai-compendium Public

    Become a cracked AI/ML Research Engineer

    JavaScript 837 120

  3. nanodl nanodl Public

    Build GPT, Gemma, LlaMa, Mixtral, Whisper, SWin, ViT and more in JAX.

    Python 301 12

  4. cuda-tutorials cuda-tutorials Public

    Comprehensive CUDA tutorials for Maths & ML with examples.

    Cuda 215 9

  5. super-lazy-autograd super-lazy-autograd Public

    Hand-derived memory-efficient VJPs for tuning LLMs on laptops.

    Python 38

  6. tango tango Public

    Decentralised ML engine to train on tiny edge devices.

    Go 6 2