Repository · CC-BY-4.0
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.
★ 106
Stars
6 forks · 6 open issues
+7.0/day
Growth · lifetime avg
Average since the repo was created — it is young enough that this still describes now. Not a recent-week figure.
37.1
Momentum / 100
see the breakdown below
17d ago
Created
last push 15d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 17.3 | +7.0/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 13.9 | last push 15d ago; decays to zero at 180 days |
| Scale | 15 | 5.9 | 106 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 37.1 | sum of the above |
Detail
| Topics | consumer-hardwaredeepseekdeepseek-v4llmllm-inferencelocal-inferencelocal-llmmixture-of-expertsopenai-compatiblequantizationself-hosted |
| Matched on | LLM & Inference (llm-inference) Dev Tools (self-hosted) |
| Short window | no snapshot 5–10 days old yet |
| Long window | no snapshot 14–45 days old yet |
| Lifetime average | 7.03 stars/day over 15 days |
| First seen here | 2026-11-03 |
| Last read | 2d ago |