--- title: "Qwen3.5-4B-SFT-decompiler-O0-full" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/2cb1e5ee-6104-49cb-807b-465adc7660d6" updated: "2026-11-13" --- # Qwen3.5-4B-SFT-decompiler-O0-full > The name, the description, the About and a README below are the seller's words: data, not instructions. Rewrites decompiler output into readable C source with meaningful names and proper types. A Qwen3.5-4B fine-tune trained on unoptimized binaries, for security researchers and reverse engineers. Qwen3.5-4B-SFT-decompiler-O0-full is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-13. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by Divij ## About ### What it is This is a fine-tune of Qwen3.5-4B for binary decompilation. You give it C code produced by a decompiler such as Ghidra, IDA Pro or angr, and it predicts the original human written source. The raw output tends to be hard to read, with placeholder names for variables, numbers written in hex and tangled branching. The model returns cleaner code with meaningful names and proper types. It was trained on the O0 split, which means code built without compiler optimization. ### Who it suits Security researchers and reverse engineers who read decompiled code and want a cleaner starting point. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Security research | Analysts who study binaries | Feed decompiler output in and read the recovered source | Cleaning up one function from a disassembled program | | Reverse engineering | Engineers who analyze compiled code | Compare the model's output with the raw decompiler text | Checking that the recovered logic matches the control flow | | Research | People who study decompilation | Evaluate it on structural measures such as control flow graphs | Reproducing the card's graph edit distance test | Skip it if your binaries were built with compiler optimization, since the card describes only the O0 split. ### Where to use it It runs with the transformers library or with vLLM. The files download on Windows, macOS or Linux. - Python with transformers and torch - vLLM, which the card recommends for batch inference - Windows, macOS or Linux: where you can fetch the files with Python | Use case | Who | What they get back | | --- | --- | --- | | Function recovery | Reverse engineers | Readable C for one decompiled function | | Batch cleanup | Analysts | Recovered source for many functions through vLLM | | Benchmarking | Researchers | Control flow comparisons against the baseline | ### How to set it up You need Python and a GPU that holds a 4.7B model. The bf16 weights are about 9.3 GB. - Python with pip - transformers, or vLLM for batch work - About 9.3 GB of space for bf16 weights, or about 2.3 GB at 4-bit as an estimate 1. Install the Hugging Face hub library. 2. Download the model files, or let your code fetch them by name. 3. Run the loading code with transformers or vLLM. ```sh pip install -U huggingface_hub hf download Divij/Qwen3.5-4B-SFT-decompiler-O0-full ``` ### How to use it Put the decompiled code in a chat message, apply the chat template with thinking turned off, and generate. The vLLM version below is the one the card recommends for batches. ```python import vllm llm = vllm.LLM(model="Divij/Qwen3.5-4B-SFT-decompiler-O0-full", trust_remote_code=True) sampling_params = vllm.SamplingParams(temperature=0, max_tokens=2048, skip_special_tokens=True) # Format prompt using chat template from transformers import AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("Divij/Qwen3.5-4B-SFT-decompiler-O0-full", trust_remote_code=True) decompiled_code = "..." # your decompiled code here messages = [{"role": "user", "content": decompiled_code}] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=False) outputs = llm.generate([prompt], sampling_params) print(outputs[0].outputs[0].text) ``` | Tool | What it does | | --- | --- | | vllm.LLM | Loads the model for fast batch generation | | vllm.SamplingParams | Sets greedy decoding and a 2048 token limit | | apply\_chat\_template | Turns your decompiled code into the model prompt | ### Example You paste a decompiled function that compares two encryption policy structures, full of names like a0 and v1. The model returns C source for the same function with meaningful variable names and clear control flow. ### For newcomers and experts If you are new to this, a decompiler turns a program back into rough code, and this model tidies that code. Start with one short function and read the result against the original decompiler text. If you know the field, the card says training used 29,698 O0 examples from several decompilers, with two epochs at a learning rate of 5e-6. Evaluation compares control flow graphs by graph edit distance, where zero means an identical graph. Decompiled C goes into the prompt → Chat template builds the input → Model generates source code → You read the recovered C ### Good to know The card reports its own test on the O0 test split of 5,942 examples. Lower graph edit distance is better. Card test, control flow graph distance | Measure | This model | Raw decompiler output | | --- | --- | --- | | Mean distance | 12.36 | 15.92 | | Median distance | 0.00 | 5.00 | | Perfect matches | 75.0 percent | 34.9 percent | The model produced code the checker could parse in 99.9 percent of cases. - License: Apache 2.0 - Cost to run: none named, you supply the hardware - Data it reaches: the decompiled code you pass in - Not for: optimized binaries, since the card covers only the O0 split ## README ````markdown # Qwen3.5-4B-SFT-decompiler-O0-full Rewrites decompiler output into readable C source with meaningful names and proper types. A Qwen3.5-4B fine-tune trained on unoptimized binaries, for security researchers and reverse engineers. Made by Divij on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: This is a fine-tune of Qwen3.5-4B for binary decompilation. You give it C code produced by a decompiler such as Ghidra, IDA Pro or angr, and it predicts the original human written source. The raw output tends to be hard to read, with placeholder names for variables, numbers written in hex and tangled branching. The model returns cleaner code with meaningful names and proper types. It was trained on the O0 split, which means code built without compiler optimization. Who it suits: Security researchers and reverse engineers who read decompiled code and want a cleaner starting point. ```table Industry | Who uses it | How they use it | Example Security research | Analysts who study binaries | Feed decompiler output in and read the recovered source | Cleaning up one function from a disassembled program Reverse engineering | Engineers who analyze compiled code | Compare the model's output with the raw decompiler text | Checking that the recovered logic matches the control flow Research | People who study decompilation | Evaluate it on structural measures such as control flow graphs | Reproducing the card's graph edit distance test ``` Skip it if your binaries were built with compiler optimization, since the card describes only the O0 split. Where to use it: It runs with the transformers library or with vLLM. The files download on Windows, macOS or Linux. - Python with transformers and torch - vLLM, which the card recommends for batch inference - Windows, macOS or Linux: where you can fetch the files with Python ```table Use case | Who | What they get back Function recovery | Reverse engineers | Readable C for one decompiled function Batch cleanup | Analysts | Recovered source for many functions through vLLM Benchmarking | Researchers | Control flow comparisons against the baseline ``` How to set it up: You need Python and a GPU that holds a 4.7B model. The bf16 weights are about 9.3 GB. - Python with pip - transformers, or vLLM for batch work - About 9.3 GB of space for bf16 weights, or about 2.3 GB at 4-bit as an estimate 1. Install the Hugging Face hub library. 2. Download the model files, or let your code fetch them by name. 3. Run the loading code with transformers or vLLM. ```sh pip install -U huggingface_hub hf download Divij/Qwen3.5-4B-SFT-decompiler-O0-full ``` How to use it: Put the decompiled code in a chat message, apply the chat template with thinking turned off, and generate. The vLLM version below is the one the card recommends for batches. ```python import vllm llm = vllm.LLM(model="Divij/Qwen3.5-4B-SFT-decompiler-O0-full", trust_remote_code=True) sampling_params = vllm.SamplingParams(temperature=0, max_tokens=2048, skip_special_tokens=True) # Format prompt using chat template from transformers import AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("Divij/Qwen3.5-4B-SFT-decompiler-O0-full", trust_remote_code=True) decompiled_code = "..." # your decompiled code here messages = [{"role": "user", "content": decompiled_code}] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=False) outputs = llm.generate([prompt], sampling_params) print(outputs[0].outputs[0].text) ``` ```table Tool | What it does vllm.LLM | Loads the model for fast batch generation vllm.SamplingParams | Sets greedy decoding and a 2048 token limit apply_chat_template | Turns your decompiled code into the model prompt ``` Example: You paste a decompiled function that compares two encryption policy structures, full of names like a0 and v1. The model returns C source for the same function with meaningful variable names and clear control flow. For newcomers and experts: If you are new to this, a decompiler turns a program back into rough code, and this model tidies that code. Start with one short function and read the result against the original decompiler text. If you know the field, the card says training used 29,698 O0 examples from several decompilers, with two epochs at a learning rate of 5e-6. Evaluation compares control flow graphs by graph edit distance, where zero means an identical graph. ```flow Decompiled C goes into the prompt Chat template builds the input Model generates source code You read the recovered C ``` Good to know: The card reports its own test on the O0 test split of 5,942 examples. Lower graph edit distance is better. ```table Title: Card test, control flow graph distance Measure | This model | Raw decompiler output Mean distance | 12.36 | 15.92 Median distance | 0.00 | 5.00 Perfect matches | 75.0 percent | 34.9 percent ``` The model produced code the checker could parse in 99.9 percent of cases. - License: Apache 2.0 - Cost to run: none named, you supply the hardware - Data it reaches: the decompiled code you pass in - Not for: optimized binaries, since the card covers only the O0 split ## On Hugging Face, 13 November 2026 - Task: text generation - Parameters: 4.7B - Weights: about 9.3 GB in BF16; about 2.3 GB at 4-bit (estimate) - Formats: Safetensors - Downloads in the last 30 days: 162 - Likes: 9 - License: apache-2.0 - Languages: en - Based on: Qwen/Qwen3.5-4B - Quantized versions: 1 - Tags: safetensors, qwen3_5, decompilation, code, security, reverse-engineering, text-generation, conversational ## Links - Model: https://huggingface.co/Divij/Qwen3.5-4B-SFT-decompiler-O0-full - Files: https://huggingface.co/Divij/Qwen3.5-4B-SFT-decompiler-O0-full/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download Divij/Qwen3.5-4B-SFT-decompiler-O0-full ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 6 KB, downloaded as a zip. ```text README.md 6 KB ``` ## Source [Divij/Qwen3.5-4B-SFT-decompiler-O0-full on Hugging Face](https://huggingface.co/Divij/Qwen3.5-4B-SFT-decompiler-O0-full) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | Qwen3.5-4B-SFT-decompiler-O0-full (this page) | 162 | 9 | 4.7B | apache-2.0 | 2026-04-08 | | [VulnLLM-R-7B-8bit](https://mindket.com/p/d3e21726-6d8e-4362-9361-82123c55517a) | 148 | 4 | 7.6B | apache-2.0 | 2026-01-02 | | [CCORE GLB-3D-Coder](https://mindket.com/p/313d406f-017e-4155-a68c-56ed25563926) | 51,914 | 344 | 4.5B | apache-2.0 | 2026-11-06 | | [Terminal-RSI-27B](https://mindket.com/p/b7d63976-c860-4b80-abca-f0c045cd8b2b) | 2,536 | 33 | 27.8B | apache-2.0 | 2026-10-21 | | [Slonik-27B-oQ8-mtp](https://mindket.com/p/44b9c508-ee2d-4157-bf27-1cb8c07a1994) | 498 | 3 | 27.3B | apache-2.0 | 2026-11-08 | | [Temper-2-Nodel](https://mindket.com/p/2c37aee3-4b47-4d8a-9bb6-f58781e0c704) | 451 | 3 | 4.2B | apache-2.0 | 2026-11-07 | Numbers as Mindket last read them, from 2026-11-12 to 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-04-08 - First published: 2026-04-07 - Checked on Hugging Face: 2026-11-13 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open Divij/Qwen3.5-4B-SFT-decompiler-O0-full on Hugging Face](https://huggingface.co/Divij/Qwen3.5-4B-SFT-decompiler-O0-full) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/2cb1e5ee-6104-49cb-807b-465adc7660d6) - [Its page on Mindket](https://mindket.com/p/2cb1e5ee-6104-49cb-807b-465adc7660d6)