---
title: IndustrialCoder-32B-FP8
canonical_url: "https://www.modelscope.ai/models/Multilingual-Multimodal-NLP/IndustrialCoder-32B-FP8"
md_url: "https://www.modelscope.ai/models/Multilingual-Multimodal-NLP/IndustrialCoder-32B-FP8.md"
repository: Multilingual-Multimodal-NLP/IndustrialCoder-32B-FP8
last_updated: 2026-03-27
license: other
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - iquestcoder
architectures:
  - IQuestCoderForCausalLM
parameters: 32.0B
tensor_type:
  - BF16
  - F8_E4M3
library_name:
  - pytorch
  - transformer
  - safetensors
frameworks:
  - pytorch
downloads: 176
stars: 0
tags:
  - code
  - industrial-ai
  - code-generation
---

# IndustrialCoder-32B-FP8

> IndustrialCoder-32B-FP8 - An open-source model by Multilingual-Multimodal-NLP on ModelScope. InCoder-32B: Industrial Code Foundation Model

Multilingual-Multimodal-NLP/IndustrialCoder-32B-FP8 is a 32.0B-parameter text-generation model on ModelScope. licensed under other.

- **Repository**: Multilingual-Multimodal-NLP/IndustrialCoder-32B-FP8
- **License**: other
- **Tasks**: text-generation
- **Parameters**: 32.0B
- **Tags**: code, industrial-ai, code-generation
- **Downloads**: 176
- **Stars**: 0
- **Last updated**: 2026-03-27

Source: https://www.modelscope.ai/models/Multilingual-Multimodal-NLP/IndustrialCoder-32B-FP8

---

# InCoder-32B: Industrial Code Foundation Model

[InCoder-32B](https://huggingface.co/papers/2603.16790) (Industrial-Coder-32B) is the first 32B-parameter code foundation model purpose-built for industrial code intelligence. While general code LLMs excel at standard programming tasks, InCoder-32B is specifically designed to address challenges in hardware semantics, specialized language constructs, and strict resource constraints.

## Model Description
InCoder-32B unifies code intelligence across several industrial engineering domains:
- **Chip Design** (Verilog / RTL)
- **GPU Kernel Optimization** (CUDA / Triton)
- **Embedded Systems** (ARM Cortex-M, STM32)
- **Compiler Optimization** (x86-64 assembly, LLVM)
- **3D Modeling** (CAD/CAM via CadQuery / OpenCascade)

The model supports a native long-context window of up to **128K tokens**.

### Links
- **Paper**: [InCoder-32B: Code Foundation Model for Industrial Scenarios](https://huggingface.co/papers/2603.16790)
- **GitHub**: [CSJianYang/Industrial-Coder](https://github.com/CSJianYang/Industrial-Coder)
- **Project Page**: [IndustrialCoder](https://huggingface.co/Multilingual-Multimodal-NLP/IndustrialCoder)

## Performance Highlights
InCoder-32B leads open-weight baselines across industrial domains and surpasses proprietary models like Claude-Sonnet-4.6 on specific benchmarks such as CAD-Coder IoU and KernelBench.

| Domain | Benchmark | InCoder-32B | Claude-Sonnet-4.6 |
|---|---|:---:|:---:|
| **Chip Design** | RealBench Func@1 (Mod) | **62.7** | 37.2 |
| **GPU Optim.** | KernelBench L1/L2/L3 | **22.2/36.0/14.0** | 11.1/28.0/2.0 |
| **3D Modeling** | CAD-Coder Compile (%) | **82.0** | 77.0 |
| **Code Optim.** | SuperCoder Acc | **91.0** | 88.0 |

## Quickstart

### Installation
```bash
pip install -U "transformers>=4.57.1" accelerate safetensors
```

### Usage with Transformers
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Multilingual-Multimodal-NLP/IndustrialCoder"

tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True,
)

messages = [{"role": "user", "content": "Optimize this CUDA kernel for better memory coalescing."}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer([text], return_tensors="pt").to(model.device)

with torch.no_grad():
    out = model.generate(**inputs, max_new_tokens=2048, temperature=0.6, top_p=0.85, top_k=20)

print(tokenizer.decode(out[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
```

## Training Pipeline
The model is trained via a three-stage **Code-Flow** pipeline:
1. **Pre-training & Annealing**: General pre-training followed by curated industrial code annealing.
2. **Mid-training**: Progressive context extension from 8K to 128K tokens using synthetic industrial reasoning data.
3. **Post-training**: Execution-grounded SFT with 2.5M samples and feedback-driven repair trajectories.

## Citation
```bibtex
@article{yang2025incoder32b,
  title={InCoder-32B: Code Foundation Model for Industrial Scenarios},
  author={Yang, Jian and Zhang, Wei and Wu, Jiajun and Cheng, Junhang and Guo, Shawn and Wang, Haowen and Gu, Weicheng and Du, Yaxin and Li, Joseph and Xu, Fanglin and others},
  journal={arXiv preprint arXiv:2603.16790},
  year={2025}
}
```

## Disclaimer
The model may generate incorrect or unsafe code. Always review and test outputs in a sandboxed environment before production use. Industrial code (RTL, embedded firmware, GPU kernels) requires expert human review before deployment.