GitHub

Magnvs7/Promethevs

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.

Stars
193
Forks
13
Stars gained in 24 hours
+2
Forks gained in 24 hours
+1

Topics: consumer-hardware, deepseek, deepseek-v4, llm, llm-inference, local-inference, local-llm, mixture-of-experts, openai-compatible, quantization

Latest data point: Nov 22, 2026 · 193 stars · 13 forks

Open on GitHub