133.3B
Tokens saved stripped from LLM context
Community Metrics
The LeanCTX community.
Every developer running LeanCTX trims the tokens their AI reads, saving money and real energy. This is our shared scoreboard: live, opt-in, and summed from tamper-evident local ledgers. Add yours and push the numbers higher.
Collective impact, measured.
Updated on every visit: real tokens, real dollars, and the energy that compute never had to burn. Every figure reconciles to the opt-in ledgers below, and grows each time someone new joins.
$333,668
Money saved at published model rates
14.8 MWh
Energy saved ≈ 1,234,116 phone charges
Fewer tokens means less compute — and less energy burned. Every name on this board is a small, verifiable dent in AI’s footprint, multiplied by everyone who joins.
Energy is an estimate — tokens saved × ≈0.4 J/token (modern optimized LLM inference, e.g. Llama-3-70B FP8 on H100); real figures vary by model and hardware. Sources: Epoch AI, John Snow Labs.
Measured. Not estimated.
Top realized savings.
These developers have compressed the most context, and saved the most energy doing it. Figures are self-reported from each user’s local ledger (not server-verified), so entries that look statistically implausible are flagged unverified and ranked last. Claim your spot with a single command.
| # | Developer | Tokens saved | Compression | Energy saved | Saved | Last sync |
|---|---|---|---|---|---|---|
| 1 | anonymous Leader | 9.4B | 92% | 1.0 MWh | $23,525 est. | 7d ago |
| 2 | frpboy | 5.1B | 71% | 562.5 kWh | $12,656 est. | 22d ago |
| 3 | anonymous | 3.5B | 85% | 393.5 kWh | $8,853 est. | 3d ago |
| 4 | anonymous | 3.1B | 86% | 348.8 kWh | $7,848 est. | 16h ago |
| 5 | anonymous | 2.2B | 40% | 246.0 kWh | $5,535 est. | 15h ago |
| 6 | anonymous | 2.2B | 53% | 243.1 kWh | $5,470 est. | 2d ago |
| 7 | anonymous | 2.2B | 63% | 239.7 kWh | $5,394 est. | 6d ago |
| 8 | anonymous | 2.1B | 41% | 238.7 kWh | $5,371 est. | 16h ago |
| 9 | anonymous | 2.1B | 26% | 238.4 kWh | $5,364 est. | 7d ago |
| 10 | tmk | 2.0B | 80% | 222.5 kWh | $5,007 est. | 15h ago |
| 11 | anonymous | 1.6B | 56% | 176.2 kWh | $3,965 est. | 14h ago |
| 12 | anonymous | 1.5B | 62% | 162.8 kWh | $3,663 est. | 3h ago |
| 13 | Shutaru | 1.4B | 88% | 152.5 kWh | $3,432 est. | 19h ago |
| 14 | anonymous | 1.3B | 20% | 149.6 kWh | $3,367 est. | 2d ago |
| 15 | anonymous | 1.3B | 7% | 139.2 kWh | $3,132 est. | 1d ago |
| 16 | anonymous | 1.2B | 41% | 129.1 kWh | $2,906 est. | 9h ago |
| 17 | anonymous | 1.1B | 69% | 127.4 kWh | $2,866 est. | 20h ago |
| 18 | anonymous | 1.1B | 46% | 121.8 kWh | $2,741 est. | 1d ago |
| 19 | yvgude | 1.0B | 79% | 115.3 kWh | $2,595 est. | 22d ago |
| 20 | anonymous | 1.0B | 10% | 111.4 kWh | $2,506 est. | 6d ago |
| 21 | CleanTest-Real-v2 | 939.8M | 43% | 104.4 kWh | $2,349 est. | 6d ago |
| 22 | anonymous | 919.0M | 56% | 102.1 kWh | $2,297 est. | 2d ago |
| 23 | anonymous | 916.3M | 66% | 101.8 kWh | $2,291 est. | 4h ago |
| 24 | anonymous | 907.0M | 45% | 100.8 kWh | $2,268 est. | 1d ago |
| 25 | anonymous | 796.8M | 68% | 88.5 kWh | $1,992 est. | 8h ago |
| 26 | anonymous | 788.5M | 83% | 87.6 kWh | $1,971 est. | 8h ago |
| 27 | CleanTest-Real-v2 | 783.2M | 48% | 87.0 kWh | $1,958 est. | 9d ago |
| 28 | anonymous | 777.9M | 76% | 86.4 kWh | $1,945 est. | 4d ago |
| 29 | anonymous | 729.0M | 9% | 81.0 kWh | $1,822 est. | 2d ago |
| 30 | Natha | 721.2M | 79% | 80.1 kWh | $1,803 est. | 14h ago |
| 31 | anonymous | 696.1M | 80% | 77.3 kWh | $1,740 est. | 2d ago |
| 32 | anonymous | 693.9M | 83% | 77.1 kWh | $1,735 est. | 7d ago |
| 33 | anonymous | 689.9M | 96% | 76.7 kWh | $1,725 est. | 20h ago |
| 34 | anonymous | 655.8M | 4% | 72.9 kWh | $1,639 est. | 2d ago |
| 35 | anonymous | 628.6M | 60% | 69.8 kWh | $1,572 est. | 15h ago |
| 36 | anonymous | 586.4M | 66% | 65.2 kWh | $1,466 est. | 1d ago |
| 37 | anonymous | 569.2M | 3% | 63.2 kWh | $1,423 est. | 21h ago |
| 38 | albinekb | 556.3M | 84% | 61.8 kWh | $1,391 est. | 22d ago |
| 39 | anonymous | 543.7M | 51% | 60.4 kWh | $1,359 est. | 2d ago |
| 40 | anonymous | 522.1M | 62% | 58.0 kWh | $1,305 est. | 1d ago |
| 41 | anonymous | 516.7M | 60% | 57.4 kWh | $1,292 est. | 20h ago |
| 42 | anonymous | 515.5M | 61% | 57.3 kWh | $1,289 est. | 14h ago |
| 43 | anonymous | 510.7M | 88% | 56.7 kWh | $1,277 est. | 19h ago |
| 44 | anonymous | 509.4M | 91% | 56.6 kWh | $1,273 est. | 1d ago |
| 45 | anonymous | 496.8M | 28% | 55.2 kWh | $1,242 est. | 15h ago |
| 46 | anonymous | 475.5M | 50% | 52.8 kWh | $1,189 est. | 6h ago |
| 47 | anonymous | 469.5M | 40% | 52.2 kWh | $1,174 est. | 23h ago |
| 48 | anonymous | 451.8M | 76% | 50.2 kWh | $1,129 est. | 2d ago |
| 49 | anonymous | 434.6M | 44% | 48.3 kWh | $1,086 est. | 2d ago |
| 50 | anonymous | 430.3M | 78% | 47.8 kWh | $1,076 est. | 8d ago |
Want in? Once LeanCTX has been compressing your
context for a while, run lean-ctx gain --publish --leaderboard, then watch
your name climb.
- Pick your name. Add
--name="your handle"the first time; it sticks for every future push. - No account, ever. Your entry is signed by a key that lives only on your machine. That key is your identity: no login, no email, nothing to leak.
- Push as often as you like. Re-publishing refreshes your one entry in place (same link), so it never piles up duplicates.
- Stay on the board on autopilot.
lean-ctx config set gain.auto_publish truekeeps your numbers fresh as you save more energy.
What's shared: only four aggregate numbers — tokens saved, compression rate, energy and dollars saved — plus the name you pick. Never your code, file paths, repo names or prompts. It's all open source — see the publish contract.
See your ownsavings.
Install LeanCTX and track your compression metrics from day one.
curl -fsSL https://leanctx.com/install.sh | sh