AI/LLM Engineer Needed to Install and Configure Powerful Local AI Model on MacBook Pro (128GB RAM) -- 2

I have recently purchased a high-performance Apple MacBook Pro with an M5 Max chip and 128GB of unified memory, specifically to run a powerful, uncensored AI language model locally.

I operate an international immigration and citizenship business and require a highly capable AI system for generating professional documents, client proposals, immigration applications, business correspondence, reports and other complex written materials.

My objective is to have a private AI assistant that functions similarly to Claude or ChatGPT, but operates entirely on my computer with significantly fewer content restrictions and refusals.

Key Requirement: Uncensored, Abliterated, Low-Refusal Model

This is a critical requirement of the project.

I specifically require an uncensored or abliterated large language model with minimal unnecessary refusals, reduced alignment restrictions and maximum flexibility in responding to legitimate user instructions.

The model must prioritise user control, instruction following, advanced reasoning and high-quality document generation rather than imposing unnecessary content restrictions.

I am not interested in installing a standard heavily restricted model.

Scope of Work

Identify and recommend the most powerful uncensored or abliterated open-weight AI model capable of running effectively on my 128GB MacBook Pro.

Install and configure the selected model using LM Studio, Ollama, MLX or another suitable platform.

Optimise performance, reasoning capabilities, context length, inference speed and output quality.

Configure the model to minimise unnecessary refusals while maintaining reliable instruction following.

Provide a professional, user-friendly interface comparable to ChatGPT or Claude.

Enable the creation, reading and editing of PDF, Word and other business documents.

Ensure all model inference and document processing operate locally without external cloud services.

Thoroughly test the system using real-world business document generation tasks.

Provide a walkthrough explaining how to operate, update and maintain the system independently.

Ideal Candidate

You must have demonstrated experience with:

Uncensored and abliterated LLMs, including low-refusal model configurations.

Apple Silicon and high-memory Mac hardware.

Local LLM deployment, MLX, LM Studio and Ollama.

Model quantisation, inference optimisation and context management.

Advanced reasoning models and professional document generation.

Configuring reliable, privacy-focused local AI assistants.

I am not looking for someone who simply downloads and installs a model. I need an experienced AI engineer who can identify the best available model for my hardware and deliver a fully configured, optimised and functional system.

Project Details

This is a one-time remote installation and configuration project.

I am ready to commence immediately and would like the system fully operational as soon as possible.

When Applying

Please provide:

The specific uncensored or abliterated model you recommend for my 128GB MacBook Pro.

Why you believe it offers the best combination of reasoning, writing quality and low refusal rates.

Your previous experience installing and optimising similar models.

Your estimated completion time and fixed project fee.

Preference will be given to candidates with direct experience deploying powerful, low-refusal AI models locally on Apple Silicon.

I am ready to hire immediately.