dorsian 🧙🏻‍♂️

Creative Director | local LLMs & art LoRa's | Ordinals | Designer

[dorsian 🧙🏻‍♂️ @Dorsian]

With local LLMs, like everywhere, hype X accounts are confusing things with bullshit.

Here are some facts I learned so far:

💎 No, 32 or 36 GB unified RAM is not enough. Ideal minimum is 64 GB.

💎 Model decision always comes down to Gemma 4 31B (or 26B MoE) or Qwen 3.5 27B (or 35B MoE). These are the only multi-use models. Question is, can you make them fast?

💎 Yes, MLX on Apple Silicon is the real deal. Without it, local LLMs are just a stunt.

👀 If you are a beginner wanting to use an LLM in GUI, use LM Studio directly and forget about other tools.

🕸️ Open WebUI works just as well with LM Studio, which is good because it gives internet access abilities to your LLM (making it actually usable).

🤯 No current local LLMs will be able to run advanced skills with OpenClaw or Hermes. At best, they can be the brains of single-use agents, nothing more.

There is a lot of hype bullshit on X. Do not fall for it; it will cost you time and money. If you need agents that get something done, accept the cost for tokens and use cloud frontier models such as Codex or Claude directly. You will not save money by buying a MacBook Pro M5 Max.

[dorsian 🧙🏻‍♂️ @Dorsian]

@thaiscbranco_ @CRV @AmplifyPartners Love this. We are might have something similar at https://t.co/FKZz2qFBGI and https://t.co/yCuXX3LD47

[dorsian 🧙🏻‍♂️ @Dorsian]

@DavidOndrej1 But is it real?

[dorsian 🧙🏻‍♂️ @Dorsian]

While we are at discussions about new billionares generated by IPOs; this is gold:

[Paul Graham @paulg]

How to Earn a Billion Dollars: https://t.co/WeWBUkKym6

[dorsian 🧙🏻‍♂️ @Dorsian]

@Youssofal_ @seangeng When would it be out?

[dorsian 🧙🏻‍♂️ @Dorsian]

@ivanfioravanti Love this idea!

[dorsian 🧙🏻‍♂️ @Dorsian]

This is exact guideline to live in AI age:

[Ali Yahya @alive_]

Barbell strategy for killing it in an age of superhuman AI:

Simultaneously get as close to AND stay as far away from AI as humanly possible.

1. Get close — play with AI models, use them to help you think, ask them to teach you about the world, get them to help you create, work with them to write code, understand what makes them tick, embed them into your everyday life, have fun.

2. Stay far away — learn to tell stories, make eye contact, build a team, lead with courage, connect far-flung ideas, build lifelong friendships, debate persuasively, think forbidden thoughts, handwrite ideas, confess your fears, fall in love.

Spend less time trying to master mental transformations that are purely mechanical — building spreadsheets, analyzing trades, balancing accounts, writing code by hand, following playbooks, searching for needles in haystacks. These are the emerging no-man's land, squarely the domain of AI.

Venture to the extremes. That’s where all the fun is anyway.

[dorsian 🧙🏻‍♂️ @Dorsian]

@KimiDevs Hey

[dorsian 🧙🏻‍♂️ @Dorsian]

@tylerxhobbs @shape ( 01 / 10 ) Tyler Hobbs

[dorsian 🧙🏻‍♂️ @Dorsian]

@neural_avb Allways go for MLX. However, dense models are naturaly slower, if you want fast model go for MoE

[dorsian 🧙🏻‍♂️ @Dorsian]

@Jason I'm in

[dorsian 🧙🏻‍♂️ @Dorsian]

@HeresMyEth No, truth is, besides posts on X, there is not much use for that due to untransparent rights.

[dorsian 🧙🏻‍♂️ @Dorsian]

As a person who has worked professionally in visual content creation for more than a decade, I find the new GPT image generator extremely annoying.

Folks, I love AI and LLMs, but what we certainly do not need right now is a new generation of slop image generators without clear usage rights and authenticity.

[dorsian 🧙🏻‍♂️ @Dorsian]

@Dennis_Porter_ The AI sloppiness of text is obfuscating the point

[dorsian 🧙🏻‍♂️ @Dorsian]

@llmdevguy True.

[dorsian 🧙🏻‍♂️ @Dorsian]

@ivanfioravanti Im looking for local coding beast, so will be watching this closely 😀

[dorsian 🧙🏻‍♂️ @Dorsian]

@amorriscode Add https://t.co/nHmlhDYXNl fair illustration generation skill for full rights on all content. It allows you to generate fair and commercially viable illustrations and animations from safetensors backed by real artists.

[dorsian 🧙🏻‍♂️ @Dorsian]

@RobertJBye Add https://t.co/nHmlhDYXNl skill for perfect mix. It allows you to generate fair and commercially viable illustrations and animations from safetensors backed by real artists.

[dorsian 🧙🏻‍♂️ @Dorsian]

@nateparrott Add Antekirt Fair Illustration skill by https://t.co/nHmlhDYXNl. It allows u to generate fair and commercially viable illustrations and animations from safetensors backed by real artists.

[dorsian 🧙🏻‍♂️ @Dorsian]

@callmejohnnie Awesome! We would love to have there https://t.co/nHmlhDYXNl skill as content placeholder filler. It allows to generate fair and commercially viable illustrations and animations from safetensors backed by real artists.

[dorsian 🧙🏻‍♂️ @Dorsian]

Anyone tested smaller quants of Qwen 3.6 for Hermes or OpenClaw?