🚀Welcome to a new generation of Minecraft with Andy 3.5🚀

Andy 3.5 is a collection of LOCAL LLM’s designed for playing Minecraft

Andy 3.5 is designed to be used with MindCraft, and is not designed nor intended to be used for any other applications

How to run

First off, open your command terminal

Enter the command ollama pull sweaterdog/andy-3.5

If you want a different model, look here and choose the model you want.

Go to your profile in MindCraft, and enter the model name that you downloaded, example: sweaterdog/andy-3.5, or sweaterdog/andy-3.5:mini-f16

What are capabilities and Limitations?

The smaller model (Andy-3.5-mini) had ¹⁄₃ of the parameters tuned.

Andy-3.5 was trained on EVERYTHING regarding Minecraft and MindCraft, it knows how to use commands natively without a system prompt.

Andy-3.5 also knows how to build / use !newAction to perform commands, it was trained on lots of building, as well as, using !newAction to do tasks like manually making something or strip mining.

What models can I choose?

There are 3 model sizes available, Regular, Mini, and Teensy

Regular is a 7B parameter model, tuned from Deepseek-R1 Distilled

Mini is a 1.5B parameter model, also tuned from Deepseek-R1 Distilled

Teensy is a 360M parameter model, tuned from SmolLM2 (This model is very unstable)

Out of all of the models, Teensy had the largest percent of parameters tuned, being ¹⁄₂ the models total size

Safety and FAQ

Q: Is this model safe to use?

A. Yes, this model is non-volatile, and cannot generate malicous content

Q. Can this model be used on a server?

A. Yes, In theory and practice the model is only capable of building and performing manual tasks via newAction

Q. Who is responsible if this model does generate malicous content? A. You are responsible, even though the model was never trained to be able to make malicous content, there is a very very slight chance it still generates malicous code.

Q. If I make media based on this model, like photos / videos, do I have to mention the Creator?

A. No, if you are making a post about MindCraft, and using this model, you only have to mention the creator if you mention the model being used.

Important notes and considerations

This model is capable of a 32k (stable) context length

This model will be given extremely niche and odd benchmarks, since no other benchmark can evaluate Minecraft performance.

For more quantizations, such as the FP16 version of Andy-3.5, they can be found here on huggingface

Performance Metrics

These benchmarks are a-typical, since most standard benchmarks don’t apply to Minecraft The benchmarks below include models via API that are cheap, and other fine-tuned local models (Excluding Andy-v2 and Andy-v3, since they are bad)

Zero info Prompting

How fast can a model collect 16 oak logs, and convert them all into sticks

Currently, Andy-3.5 and Andy-3.5-mini are the ONLY models that can play without command documentation, or any other instruction, and Andy-3.5-Mini sometimes fares better without the unnecessary data. Test this for yourself using this profile

Time to get a stone pickaxe

I am sure other models like Deepseek-R1 may be faster at getting a stone pickaxe, however the Demo was to show the performance of Andy-3.5

For Andy-3.5-mini, I used the FP16 model, I had enough VRAM to do so For Andy-3.5, I used the Q4_K_M quantization For Andy-3.5-Teensy, I used the FP16 quantization For Mineslayerv1 and Mineslayerv2, I used the default (and only) quantization, Q4_K_M

Notes about the benchmarks

Zero Info Prompting

Andy-3.5-Teensy was able to use one command successfully, but was not able to afterwards

Andy-3.5-Mini collected 32 oak_log instead of 16 oak_log

Andy-3.5 attempted to continue playing, and make a wooden_pickaxe after the goal was done.

Both Mineslayerv1 and Mineslayerv2 hallucinated commands, like !chop or !grab

Time to get a stone pickaxe

Andy-3.5-teensy hallucinates too much for stable gameplay (It is a 360M parameter model, what can be expected)

Andy-3.5-Mini was unable to make itself a stone pickaxe, however it collected enough wood, but then got stuck on converting logs to planks, it kept trying “!craftRecipe(“wooden_planks”, 6) instead of oak_planks

Andy-3.5 Made a stone pickaxe the fastest out of all models, including GPT-4o-mini and Claude-3.5-Haiku

Mineslayerv1 Was unable to use !collectBlocks, instead kept trying !collectBlock

Mineslayerv2 Was unable to play, it kept hallucinating on the first command