GhidrAssist

At a glance

Best for

Asking questions about a binary from inside Ghidra, with everything kept on your machine.

Inference engine

• uses Ollama, LM Studio or any OpenAI-compatible server

GPU support

None of its own: it talks to a llama.cpp or MLX LM server

Opens

• GGUF
• MLX

Features

• Chat window
• Tool calling
• Agent workflows

Platforms

Runs inside Ghidra (free, from the NSA) on macOS, Windows and Linux.

Install

Then set its API host to your local server, for example http://localhost:11434 for Ollama or http://localhost:1234/v1 for LM Studio.

14 models on this site run in GhidrAssist

Models tagged for reverse engineering that follow instructions, with a GGUF or MLX build to serve locally. Raw decompilers such as LLM4Decompile run on their own in llama.cpp or LM Studio instead.

Model	Made by	Type	Size	Opens it as	Quality tier
Qwen3.5 27B	Alibaba	LLM	28B	GGUF or MLX	93
Qwen3.5 35B-A3B	Alibaba	LLM	36B (3.0B active)	GGUF or MLX	93
DeepSeek R1 (671B)	DeepSeek	LLM	671B (37.0B active)	GGUF or MLX	92
ZAGLM-4.7 Flash (30B-A3B)	Zhipu AI	LLM	31B (3.0B active)	GGUF or MLX	88
Devstral 2 (123B)	Mistral AI	LLM	125B	GGUF or MLX	86
OAgpt-oss 120B	OpenAI	LLM	117B (5.1B active)	GGUF or MLX	84
Qwen3 Coder 30B-A3B	Alibaba	LLM	31B (3.3B active)	GGUF or MLX	78
DeepSeek V3 (671B)	DeepSeek	LLM	671B (37.0B active)	GGUF or MLX	75
Qwen3 30B-A3B	Alibaba	LLM	31B (3.3B active)	GGUF or MLX	74
Gemma 3 27B IT	Google	LLM	27B	GGUF or MLX	72
OAgpt-oss 20B	OpenAI	LLM	21B (3.6B active)	GGUF or MLX	70
Qwen3 8B	Alibaba	LLM	8.2B	GGUF or MLX	60
CFFoundation-Sec 8B Reasoning	Cisco Foundation AI	LLM	8.0B	GGUF	52
CFFoundation-Sec 1.1 8B Instruct	Cisco Foundation AI	LLM	8.0B	GGUF	50

Alternatives

IDA Pro MCP GhidraMCP Gepetto JADX AI MCP ReVa r2ai and decai OGhidra BinAssist

Which app should I use?