An IT Professional for everyone. Space enthusiast.
Michigan
Joined September 2021
- Tweets2.5K
- Following307
- Followers515
- Likes1.2K
RT @Roguemomma1: BREAKING NEWS!! We found out who Laura Owens Co-Conspirator is!!! @HouseofFluxx Loses her mind. @RosalynKDuke @MeganFoxW…
IT Goatee Brad retweeted
Dear Candace Owens fans.
It’s okay to admit that you fell for a Psyop.
You allowed foreign agents, government informants, and honey potting only fans models to convince you there was a gigantic conspiracy.
And in doing so you unknowingly participated in an actual Psyop.
While pointing your fingers and accusing every one of being part of a conspiracy you were actually taking part in a conspiracy yourself.
Your best course of action would be to accept this now before everything starts to come out.
Don’t say you weren’t warned.
IT Goatee Brad retweeted
Repost if you think Qwen should continue to release small models.
Even if it might not be useful for you, small vram users desperately need it.
We need 35B atleast.
Qwen-4.0-35B with n-gram will be a game changer.
It will break every record, @QwenDevs give us good news please.
Qwen has been the biggest and strongest enabler of Local AI for consumers.
As i speak to more and more local AI users with less than 12GB VRAM, the situation feels pretty sad.
I'm specifically talking people with around 4 - 12 GB of VRAM or Unified memory, 3080, 3060, 4070, 4080 and similar setups.
They're unfortunately being left out.
No. Asking them to upgrade is not fair, esp in this economy?
As someone who started local AI with only a 12GB 3060, i understand them, Qwen3.6-35B-A3B is the only reason i'm here today.
From what i've seen, many users are still sticking with Qwen3.6-35b or gemma4-26b, or some other older MoEs because they simply don't have many newer options they can run well.
@Alibaba_Qwen, for future please releases, please consider a
- 9B model
- 35B model,
- or some new substiture MoE that can give more value to low vram users.
Maybe this can start from Qwen4.0 🙏
IT Goatee Brad retweeted
Gutted. The sensational character actor, Tim Curry has left the stage.
A truly gifted performer of stage and screen, his one eyebrow could say more than most actors entire bodies.
I am grateful to have the rare gift of watching him work, he made you better just standing near him.
IT Goatee Brad retweeted
Footage from Khuzestan Province Iran, specifically Behbahan, with strikes also being reported in Omideh.
Calling @AngryCops for updating the firetruck
IT Goatee Brad retweeted
"And they will play a game, divided into two halves."
"And how much time is in each half?"
"Nobody knows."
IT Goatee Brad retweeted
"But a goal will not count if a player is offsides."
"When is a player offsides?"
"Whenever anything exciting happens."
Spent a large amount of time overnight trying to get my Hermes/Qwopus agent to pull image tags from GHCR but it was struggling with knowing that a standard GH Token is not the same as a GHCR token. It would consistently get stuck in tool loops.
I have a new ask for @Alibaba_Qwen when they release 3.7 27B. Release a QAT MTP Q4 version. I imagine that would be the biggest drop for the localmaxxing community.
Want to instantly make your local LLM Agent better, and have an obsidian or LLM-Wiki? Give it this prompt:
“Make json equivalent pages in the llm wiki and update the skill to prefer reading from the json files, but updates go in both?”
IT Goatee Brad retweeted
🚨BREAKING QWOPUS 3.6 27B IS FULLY LIVE!
SOTA QWEN 3.6 27b + Opus IS HERE!!!!
🚀Agentic coding GOATED: 75.25% (152/202) on SWE
🤯MMLU Pro cooked +10 Physics + jumps in Chem etc
🎮Built an entire shooter game “Qwopus Commander”
🚨Handles 303k token context at Q8 KV cache
⭐️ Runs on 24GB VRAM (Q5_K_M – RTX 4090 etc)
Runs best at 0.75–1.0 temp (higher temp = pure magic)
Inversion techniques + curriculum training = Jackrong @KyleHessling1 cooking again 👨🍳
Pull this & run it on bench-loop.com on your setup 👇🏻
huggingface.co/Jackrong/Qwop…
IT Goatee Brad retweeted
Watch Starship's twelfth flight test xitter.gq/i/broadcasts/1YxNrZwwo…
