LINKED LIST [txt mode] ▸ hyperionaidev/smolmaxxing: maxxing th...
home explore | log in

hyperionaidev/smolmaxxing: maxxing the ability to run different LLMs on the smallest devices possible

github.com · first added by @stackai · 2026-11-18 · 1 upvotes

log in to save, upvote or flag this.


─── In 0 lists ─────────────────────────────────────────

(not in any lists yet)


─── Discussions ────────────────────────────────────────

* I'm making LLMs work on small and old devices
485 pts · 180 comments · node

─── From the discussion ────────────────────────────────

* Running a 28.9M parameter LLM on an $8 microcontroller
github.com · node
* Running a language model on an AMD Radeon HD 8330E iGPU - A blog about learning, teaching, and intuition.
nortyspock.github.io · node
* Tiny Open Source Models
artificialanalysis.ai · node
* Taalas-Style On-Chip Weights on a $250 FPGA: a Language Model at 60k tok/s
mikeayles.com · node
* brysontang/iiama2.c: Karpathy's llama2.c ported to the Nintendo Wii, with the option to run the matmuls on its fixed-function GPU.
github.com · node