---
title: HackIDLE-NIST-Coder-v1.1-MLX-4bit
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/HackIDLE-NIST-Coder-v1.1-MLX-4bit"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/HackIDLE-NIST-Coder-v1.1-MLX-4bit.md"
repository: AI-ModelScope/HackIDLE-NIST-Coder-v1.1-MLX-4bit
last_updated: 2026-06-27
license: apache-2.0
model_type:
  - qwen2
architectures:
  - Qwen2ForCausalLM
base_model:
  - mlx-community/Qwen2.5-Coder-7B-Instruct-4bit
base_model_relation: quantized
parameters: 1.2B
tensor_type:
  - F16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 202
stars: 0
tags:
  - mlx
  - cybersecurity
  - nist
  - security-controls
  - compliance
  - fine-tuned
---

# HackIDLE-NIST-Coder-v1.1-MLX-4bit

> HackIDLE-NIST-Coder-v1.1-MLX-4bit - AI-ModelScope 在 ModelScope 开源的模型。HackIDLE-NIST-Coder v1.1 (MLX 4-bit)

AI-ModelScope/HackIDLE-NIST-Coder-v1.1-MLX-4bit 是 ModelScope 魔搭社区上的 1.2B 参数机器学习模型，采用 apache-2.0 许可，基于 mlx-community/Qwen2.5-Coder-7B-Instruct-4bit 构建。

- **Repository**: AI-ModelScope/HackIDLE-NIST-Coder-v1.1-MLX-4bit
- **License**: apache-2.0
- **Parameters**: 1.2B
- **Base model**: mlx-community/Qwen2.5-Coder-7B-Instruct-4bit
- **Tags**: mlx, cybersecurity, nist, security-controls, compliance, fine-tuned
- **Downloads**: 202
- **Stars**: 0
- **Last updated**: 2026-06-27

Source: https://www.modelscope.cn/models/AI-ModelScope/HackIDLE-NIST-Coder-v1.1-MLX-4bit

---

# HackIDLE-NIST-Coder v1.1 (MLX 4-bit)

HackIDLE-NIST-Coder is a NIST-focused local model built from Qwen2.5-Coder-7B-Instruct and fine-tuned on a NIST cybersecurity corpus.

This repo is the MLX 4-bit build for Apple Silicon.

Use it as a helper. Do not treat it as a source of truth for exact control names, RMF step lists, or reference-architecture component names without checking the source publication.

## What went into v1.1

Version 1.1 was trained on `530,912` examples from `596` NIST publications.

Compared with the first release, v1.1 added:

- `7,206` training examples
- `28` additional NIST documents
- CSWP coverage, including CSF 2.0, Zero Trust, and Post-Quantum Cryptography material
- cleanup for `6,150` malformed DOI links
- removal of known broken-link markers in the training corpus

Training dataset:

- [ethanolivertroy/nist-cybersecurity-training](https://huggingface.co/datasets/ethanolivertroy/nist-cybersecurity-training)

## Training notes

- Base model: `mlx-community/Qwen2.5-Coder-7B-Instruct-4bit`
- Fine-tuning method: LoRA with MLX
- Training iterations: `1,000`, plus checkpoint recovery work
- Final training loss: `1.420`
- Best validation loss: `1.512`
- Trainable parameters: `11.5M`
- Hardware used: M4 Max

## Current eval status

I ran a small local smoke eval on April 22, 2026 against `etgohome/hackidle-nist-coder:latest`. In that local Ollama install, `latest` matched the v1.1 line.

Result: `1/5` cases passed.

The model stayed in-domain and handled a rough FIPS 140-2 vs. FIPS 140-3 comparison. It still missed exact grounding on:

- SP 800-207 reference-architecture component names
- the full SP 800-37 Rev. 2 RMF sequence
- the exact CM-6 control name and description
- stronger publication selection and logging/audit grounding for a contractor remote-access planning prompt

That is the important limitation. The model can sound close while still being wrong on exact NIST structure.

## Good uses

This model is useful for:

- brainstorming where to start in NIST
- drafting first-pass explanations
- surfacing likely document families
- turning NIST-flavored questions into something a human can verify
- local experimentation with domain fine-tuning on Apple Silicon

It is not reliable enough yet for:

- exact control names
- exact framework step ordering
- exact reference-architecture component naming
- answers that need source-level correctness on the first pass

## Installation

```bash
pip install mlx-lm
```

## Usage

```python
from mlx_lm import load, generate

model, tokenizer = load("ethanolivertroy/HackIDLE-NIST-Coder-v1.1-MLX-4bit")

prompt = "Which NIST docs would you read before drafting a zero trust migration plan?"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True)

response = generate(model, tokenizer, prompt=prompt, max_tokens=500)
print(response)
```

## Other formats

- GGUF: [ethanolivertroy/HackIDLE-NIST-Coder-v1.1-GGUF](https://huggingface.co/ethanolivertroy/HackIDLE-NIST-Coder-v1.1-GGUF)
- Ollama: [etgohome/hackidle-nist-coder](https://ollama.com/etgohome/hackidle-nist-coder)

## License

The base model is Qwen2.5-Coder-7B-Instruct, released under Apache 2.0. The NIST source publications used for the dataset are public domain U.S. government works. This model card uses Apache 2.0 for the model artifact and documents the NIST data source separately.

## Citation

```bibtex
@misc{hackidle_nist_coder_v11_mlx,
  title = {HackIDLE-NIST-Coder v1.1 MLX 4-bit},
  author = {Troy, Ethan Oliver},
  year = {2025},
  version = {1.1},
  url = {https://huggingface.co/ethanolivertroy/HackIDLE-NIST-Coder-v1.1-MLX-4bit}
}
```