@bepleecanton @garrytan I’m using tei cpu only embedding server
English
Your Highness
555 posts
Your Highness
@yourhighnessLA
High quality cannabis cultivators in Los Angeles. Operating in California, Nevada, Massachusetts, Michigan, & more. Clothing available @ Zumiez, Spencer’s.
Los Angeles Katılım Ekim 2014
301 Takip Edilen1.3K Takipçiler
if you ran qwen 3.6 27b dense locally yet, drop your numbers. doesn't matter what hardware. 3090, 4090, 5090, mac series, anything. share your tok/s, your quant, your harness, and what your agent built locally with this model. community wins when we all share. saves the next person hours of head scratching.
English
first test results are in. qwen 3.6 27b dense just banged 10 out of 10 on a single rtx 3090 24gb tier at 40 tok/s. no quant tricks. no fused kernels. just q4_k_m straight cut on llama.cpp.
i wrote a particle swarm benchmark this morning, fed it the prompt, and the model autonomously built a 500 particle boids flocking system. velocity driven hue, density based brightness, trail blend rendering, mouse attraction physics, click bursts, drag paint. then it used browser automation to test its own work, found the failing tests, iterated through the code, patched tests.js, and landed all 10 green on its own.
i sat there hooked for 8 minutes playing. simple but mesmerizing. mouse trails build beautiful patterns, palette cycles with space, click sends particles flying, drag paints through the swarm. simplicity that hooks you.
i'll open source this prompt and the build soon so anyone can reproduce it as their own benchmark. this is the first of 5 single file agent tests i wrote for this model. four more coming. octopus invaders flagship after as final.
watch the full video below. see it autonomously build from one prompt. haven't slept well since this model dropped yesterday.
Sudo su@sudoingX
qwen 3.6-27b dense q4 on a single 3090 just knocked down 10 out of 10 tests at 40 tok/s on the first particle swarm benchmark i wrote for local agentic coding. it built the two files exactly to spec. then it used browser automation tools to open the page, read the test hud, find the failing tests, iterated through the code, patched tests.js, adjusted hue mapping, boosted mouse attraction force, and landed all 10 green checkmarks. this was actual dev behavior. not just generating code but also debugging its own output. i spent the next 8 minutes playing with the result. the boids flocking feels alive, the trail-blend is cinematic, three palettes cycle with space, mouse burst fires particles from click, drag paints a line through the swarm. this is what local ai looks like now. single 3090. hermes agent. no frameworks. no tricks. dropping the video next.
English
🚨 BREAKING: R.I.P. CLICKFUNNELS.
Opus 4.6 ONE-SHOTS entire VSL funnels now.
I compressed my entire VSL framework into a single 5,280-word prompt.
The same framework that's generated $1M+ and 500+ booked calls.
HOW IT WORKS:
You plug in your offer details. It spits out:
→ Full VSL script from hook to close
→ Built on the persuasion structure behind EVERY high-converting agency funnel
→ Generated $1M+ and 500+ booked calls
This thing can INSTANTLY double your booked calls.
Use it now or get left behind. 🤘
Like + reply "OPUS" and I'll DM it to you
English
I run my meta ads with @openclaw for $0/month 😱
here's the system that runs autonomously:
step 1: daily health check
→ social-cli (major shoutout to @vishalojha_me) wraps @Meta's marketing API (token refresh, pagination, rate limits all handled)
→ am I on track? what's running? who's winning? who's bleeding? any fatigue?
→ the same 5 questions I asked Ads Manager every morning for 20 years
step 2: catch dying ads before CPA spikes
→ @OpenClaw pulls daily frequency by ad
→ frequency > 3.5 = audience is cooked, CTR is about to drop
→ this one signal saves more money than any dashboard
step 3: auto-pause bleeders + shift budget to winners
→ CPA > 2.5x target for 48hrs? auto-pause. no hesitation.
→ ranks every campaign by efficiency. recommends shifting spend.
→ last fri it paused an $87 CPA campaign at 3am and scaled my best performer 30%
step 4: write new ad copy from your winners
→ agent analyzes what's working (hooks, angles, CTAs)
→ generates variations based on the patterns in YOUR top performers
→ copy modeled on what already converts in your account.
step 5: upload ads directly to your account
→ new creative + copy
→ live in @Meta Ads Manager
→ no more downloading, formatting, clicking through the upload flow
→ agent handles the entire publish cycle
step 6: content concepts + morning brief
→ spots patterns across winners and suggests what to test next
→ delivers everything to Telegram, Slack, wherever you want it
→ 90 seconds to read. reply "approved." done.
input: your ad account + your target CPA
output: an AI that monitors, kills, scales, writes, AND uploads your ads
dozens of hours in ad manager → 1 text message
I packaged the entire system as the Meta Ads Kit.
5 @OpenClaw skills:
- meta-ads (daily checks + auto-pause)
- ad-creative-monitor (fatigue detection)
- budget-optimizer (efficiency scoring + shift recs)
- ad-copy-generator (writes variations from your winners)
- ad-upload (publishes creative directly to your account)
giving it away free.
comment ADS + like + follow
(must follow so i can DM)
English
Your Highness retweetledi
English
This happened during a windy night where power lines were arcing. We had literally just taken over the spot and this was our second run. We weren’t supposed to enter, but our goal was to grab two things…our genetics if they were salvageable, and the DVR. Long live the grind.
English
Your Highness retweetledi
Tropical Pressure,Shirley Temple, Bubble Blast #YourHignessLA #CannabisCommunity #WeedLovers #highlife #highsociety
English
Your Highness retweetledi
Your Highness retweetledi
