SimboKlice

At this point I gotta learn Mandarin. America is becoming a shell of itself. Yaw think China go room for 1 more?

Lebron lost this game with back to back turnovers in the last 1:45 seconds of the 4th quarter

@kevinblue345 I need bro in Cali.

We NEED more black people in general in healthcare because WHITE providers couldn’t care less. If you’re offended, kick rocks. 🫶🏾

@gkisokay Now you gotta do a 64gb line up

The Local LLM Cheat Sheet for your 32GB RAM device I was asked to put together a practical lineup of local models that fit comfortably on a 32GB machine. At this tier, you start getting access to real flagship-class local models, plus a growing number of custom quants. But for most people, these are the core models worth knowing first. Flagship Models Qwen3.5 27B / GGUF / Q6_K_M The best overall 32GB flagship. General chat, writing, research, and agent workflows. Great if you want one model that can handle almost everything well. Qwen3.6-35B-A3B / GGUF / UD-Q4_K_M Best MoE flagship. Stronger for coding, reasoning, and tool use than most smaller generalists. Gemma 4 31B / GGUF / Q6_K_M Dense premium model. Writing, analysis, reasoning, and high-end local chat. Heavier than the MoE options, but excellent when quality matters more than speed. Models for Fast Flagship Use Gemma 4 26B A4B / GGUF / Q6_K_M Great balance of speed and quality for general assistant work, coding, agent tasks, and research. This is one of the best 32GB picks if you want something that feels high-end without dragging. DeepSeek-R1 Distill Qwen 32B / GGUF / Q4_K_M Offline reasoning engine. Best for math, logic, deliberate analysis, and step-by-step problem solving. Mistral Small 24B / GGUF / Q6_K_M Tool-calling specialist. Strong for assistants, chat workflows, local business tasks, and function calling. Available for 24GB machines. Models for Companion Use Qwen3.5 9B / GGUF / Q6_K_M Best sidekick. Fast drafts, search loops, cheap retries, and secondary agent work. Even on a 32GB machine, you still want a smaller model around for support tasks. Llama 3.1 8B / GGUF / Q6_K_M Long-context companion. RAG, doc ingestion, codebase chat, and long prompts. The output quality is not the sharpest anymore, but it is still useful when needing simple tasks fast. From what my community tells me, the best single models are Qwen3.5 27B or Gemma 4 31B. For two models, the strongest general pairing is Qwen3.5 27B + Qwen3.5 9B. If you are more code-heavy, Qwen3.6-35B-A3B + Llama 3.1 8B. Let me know what models you are running on 32GB, and which ones have actually been worth the RAM.

@nukeru_gofile Shiori Tsukada missing so list seems incomplete

@Enywealthh_1 “…get back come with time” -Posted At by Lil Durk

A perfect comeback 🤣🤣

@LeakerApple Incoming… MacBook Neo+ with A19Pro

Apple has reportedly underestimated the sales of the MacBook Neo and now they're in a pickle. MacBook Neo has been selling extremely well, and usually that would be a good thing. But the problem is that it uses binned A18 Pro chips (1 fewer GPU core). Apple only had 5-6 million leftover binned A18 Pro chips, which were unfit for the iPhone, making them essentially "free" for the Neo. This helped keep costs low while maintaining margins. However, with the high demand for the Neo, Apple is on track to run out of the binned chips. They will either have to restart production of the A18 Pro and pay a premium to TSMC (tanking profit margins), stop selling the Neo entirely, or release the A19 Pro MacBook Neo early. Although the last option is unlikely (and could result in the same issue), it is definitely possible.

@GithubProjects @huggingface is a learning curve. More Lmstudio and Ollama integration needs to happen for the models available.

Those who use Hugging Face models are way ahead.

@BernardObo19 @grok who is this woman?

@mrmikeMTL Ice juice

People that stopped drinking soda, what did you replace it with??

@elonmusk Buy my car and I’ll convert.

And they’re better cars

I have a Toyota Avalon and thought about buying a @Tesla Models S but @elonmusk is discontinuing it. Bummer.

@amateurthroat @Deepthroat17269 What’s here name?

Wife that throat up 💍

@JOKAQARMY1 Sorry, I’m distracted by how fine that woman is.

2026 predictions 🤔

@AfroStunnerz @grok make her clothes electrical tape

Baby phat

@ohhanxiety Blood type O+

any secret?

@ArtellBlender Can’t wait.

[Auto-Rig Pro update log] AI facial landmarks are on their way! Not razor sharp yet, but it's getting somewhere.

@Naam_kafi_hai Everyday

When was the last time you called it "Twitter"?

@afeso_art I love this. Share the sauce.

Cooking...

@Fidz3D ZBrush?

the headlights aren't done yet (aswell as everything else i think,,,,,)