Projects done with substantial help of Average Intelligence tools have "Slop" in their name. Others untouched.
Of course "AI" is a great to get stuff done fast, but it's quite dumb and have to be very carefully guided.
Some people compare it to a parrot facerolling on the keyboard.
LLM is not even a neural network, it's an autocomplete dictionary for T9 text predictions just like in old phones.
Repeatedly tap on your phone's text predictions - this is the current state of "AI".
Now with proper expectations you're ready to start building.
Oh, BTW. If you don't want to feed money to cloud services - start with your own local LMStudio/ComfyUI machine.
All you need is 12GB GPU and 32GB RAM to start, CPU doesn't matter. It's really that cheap.
Setup takes 3 weeks of pure suffering and you're ready for a true AI future, it'll pay off in less than a year.
Our videocards now can not only run games, but write somewhat useful code. That's pretty cool right?
And if part of your job or pipeline can actually be replaced by a parrot, maybe it should be replaced.
Think of writing and updating tests. If you're blank-staring at the wall right now, you get it.
Don't let LLMs think for you or build an architecture - it's all harmful random garbage.
Sweet spot: 32-40GB GPU VRAM + 64GB RAM
Gemma 4 31B ~100k - unsloth/gemma-4-31b-it@q5_k_xl (temp 0.3, top k 40, rep penalty 1.1)
Qwen 3.6 27B MTP ~150k - unsloth/qwen3.6-27b-mtp@q6_k_xl (temp 0.3, top k 20, no rep penalty, Q8 KVCache)
Xortron ~200k - xortron.criminalcomputing.2026.27b.next@q6_k (temp 0.3, top k 40, rep penalty 1.1)
Usable, but very low context window: 24GB GPU VRAM + 64GB RAM
Gemma 4 31B QAT 32k - unsloth/gemma-4-31b-it-qat@q4_k_xl (temp 0.3, top k 40, rep penalty 1.1)
Qwen 3.6 27B MTP 80k - unsloth/qwen3.6-27b-mtp@q4_k_xl (temp 0.3, top k 20, no rep penalty, Q8 KVCache)
Xortron 40k - xortron.criminalcomputing.2026.27b.next@q5_k_m (temp 0.3, top k 40, rep penalty 1.1)
A bit more advanced than starter: 16GB GPU VRAM + 32GB RAM
Xortron 32k - xortron.criminalcomputing.2026.27b.next@iq3_xs (2 layers on CPU, Q8 KVCache, temp 0.3, top k 40)
Starter option, pretty useless dumb models: 12GB GPU VRAM + 32GB RAM
Gemma 4 12B QAT 80k - unsloth/gemma-4-12b-it-qat@q4_k_xl (temp 0.1, top k 40, rep penalty 1.1)
--
Global settings: Min P Sampling 0.05, Top P Sampling 0.95.
This is how these settings work (yeah I know, pretty much every IT video).
If you can get anything done on a small model, get a dual-16GB-GPU setup. I use dual RTX 4000 Ada for 40GB VRAM.
Every 8GB extra VRAM is an astronomic leap in quality. 16GB models are not even close to 24GB models.
Use OpenAI-compatible API to connect to LM Studio. The https://zed.dev/ seems to be best open-source agentic IDE.
Here are jinja templates for LM Studio and Zed. Very tedious to get right.
Put Responses MUST be terse and short. in a rule or system prompt, or use my PortableAgent ruleset.
Vision consumes a lot. Use Q8_0 or BF16 .mmproj files so you don't have to blind the model completely.
I use low temperatures and top K to avoid tool use typos/screwups, since I use LLMs mostly for routine like refactoring.
To avoid Gemma 4 thinking bugs, use "<|channel>" as your reasoning start string, not "<|channel>thought".
All models should use 8k output token limit except Qwen 3.6 that needs 32k.
Always disable Unified KV Cache and set Max Concurrent Prediction to 1, unless model is intended to work in parallel.
- com.bananaparty.unislop - Minimalistic portable Unity MCP server designed for coding.
- com.bananaparty.touchinput - Comfortable abstraction with gesture support for unity's touches.
- com.bananaparty.websocketclient - Fully cross-platform websocket client.
- ComfyUI-Enhancement-Utils - PC resource monitor and execution follower.
- ComfyUI-SloppyAudio - Audio editing tools based on SoX and BS-RoFormer.
- smol-caveman - Portable Caveman prompt designed for local LLMs. Read less slop and get much better results.
- ComfyUI-SloppyInstall.bat - Simplified pip install -r "requirements.txt" for custom nodes in portable ComfyUI.
- SloppyServer.bat - Single file local/Wi-Fi server for debugging multithreaded mobile Unity WebGL builds.