PROMETHEVS: run the full DeepSeek-V4.1-Flash-1017 (510 GB) on a gaming PC with 64 GB RAM and a 12 GB GPU. PROMETHEVS engine (compress-then-correct), OpenAI-compatible local server, report and logs.
Repository Index
54,641 visible repositories in the index
25–28 of 28 · Most stars
PrismQuant: Optimal Null-Space Rotations for Grouped Quantizers
- int4
- large-language-models
- pytorch
- quantization
Legend of Elya — N64 game with a real 6.36M-parameter ternary transformer on the VR4300 MIPS III CPU. Zelda-style dungeon, AI NPCs, byte-level inference at 1.23 tok/s scalar / 2.19 tok/s on the RSP overlay (measured under ares, never on silicon). Built with libdragon.
Color quantization and dithering in TypeScript.