Updated November 18, 2026
Glossary ToolsBest models

Models · on your own machine

Local LLM for reverse engineering

The local LLM for reverse engineering in an air-gapped lab is Qwen 3.8 27B Abliterated. It is about 17 GB at 4-bit and fits one 24 GB GPU or a 32 GB Mac.

By AI for Reverse EngineeringUpdated November 18, 2026
On this page

Models that fit

ModelParametersSize at 4-bitRuns onLicense
Qwen 3.8 27B Abliteratedhuihui-ai/Huihui-Qwen3.8-27B-abliterated27.8Babout 17 GBone 24 GB GPU or a 32 GB MacApache 2.0
Qwen 3.6 35B-A3B Abliteratedhuihui-ai/Huihui-Qwen3.6-35B-A3B-abliterated36B total, 3B activeabout 22 GBone 24 GB GPUApache 2.0
Gemma 4 31B Hereticcoder3101/gemma-4-31B-it-heretic31.3Babout 19 GBone 24 GB GPUApache 2.0
Llama 3.1 8B Abliteratedmlabonne/Meta-Llama-3.1-8B-Instruct-abliterated8Babout 5 GBan 8 GB GPU or a laptopLlama 3.1 Community License

From each model's Hugging Face page, read November 18, 2026. Sizes at 4-bit are estimates.

Qwen 3.8 27B Abliterated. Its GGUF build had over 4.3 million downloads in the last month. Qwen 3.6 35B-A3B Abliterated. Its MTP GGUF build had over 5 million downloads in the last month. Gemma 4 31B Heretic. Abliterated with the Heretic tool. Llama 3.1 8B Abliterated. Published by mlabonne, whose 2024 write-up made abliteration popular.

When to run locally

These models are 8B to 36B parameters. Kimi K3.1 Pro is 2,780B and writes up to 943,718 tokens.

Plugins

ToolLocal servers in its READMESetting
Gepetto (IDA Pro)Ollama, LM StudioEditGepetto, or BASE_URL in config.ini
r2ai (radare2)Ollama, LM Studior2ai -e api=openai and r2ai -e baseurl=http://LM-STUDIO-IP:PORT
GhidrAssist (Ghidra)Ollama, LM Studio, Open-WebUIProvider type Ollama, URL http://localhost:11434
IDAssist (IDA Pro)OllamaType ollama, URL http://localhost:11434
BinAssist (Binary Ninja)Ollama, LM Studio, Open-WebUIAPI Host http://localhost:11434

An MCP agent can use the same address. See the MCP setup page.

Trade-off

A 27B model names simple functions and drops details in long ones. Rerun the hard ones on a larger model.