Instructions to use i-Coder/iCoder-27B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use i-Coder/iCoder-27B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="i-Coder/iCoder-27B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("i-Coder/iCoder-27B")
model = AutoModelForMultimodalLM.from_pretrained("i-Coder/iCoder-27B", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use i-Coder/iCoder-27B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "i-Coder/iCoder-27B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "i-Coder/iCoder-27B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/i-Coder/iCoder-27B

SGLang

How to use i-Coder/iCoder-27B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "i-Coder/iCoder-27B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "i-Coder/iCoder-27B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "i-Coder/iCoder-27B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "i-Coder/iCoder-27B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use i-Coder/iCoder-27B with Docker Model Runner:
```
docker model run hf.co/i-Coder/iCoder-27B
```

greeky commited on 4 days ago

Commit

5858b51

1 Parent(s): 2cde19b

Add iCoder technical report

Browse files

Files changed (3) hide show

.gitattributes +1 -0
Coder_Tech_Report.pdf +3 -0
README.md +20 -2

.gitattributes CHANGED Viewed

@@ -37,3 +37,4 @@ tokenizer.json filter=lfs diff=lfs merge=lfs -text
 figures/industrial_benchmark_logo_bars.png filter=lfs diff=lfs merge=lfs -text
 figures/intro_pipeline.png filter=lfs diff=lfs merge=lfs -text
 figures/title.png filter=lfs diff=lfs merge=lfs -text

 figures/industrial_benchmark_logo_bars.png filter=lfs diff=lfs merge=lfs -text
 figures/intro_pipeline.png filter=lfs diff=lfs merge=lfs -text
 figures/title.png filter=lfs diff=lfs merge=lfs -text
+Coder_Tech_Report.pdf filter=lfs diff=lfs merge=lfs -text

Coder_Tech_Report.pdf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:08e803d8e5229b498c16c79b47340a69b528d01c079ac3336bab5c1f5dde9795
+size 6574345

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ tags:
   <img src="figures/title.png" alt="iCoder-27B" width="420">
 </p>
-<div align="center"><a href="https://github.com/bingreeky/iCoder"><img src="https://img.shields.io/badge/GitHub-iCoder-181717?logo=github&logoColor=white" alt="GitHub"></a> <img src="https://img.shields.io/badge/Technical%20Report-coming%20soon-9c9c9c" alt="Technical Report"></div>
 iCoder-27B is a 27B-parameter model for industrial coding, covering RTL design
 and GPU kernel optimization.
@@ -38,7 +38,8 @@ RTLLM (68.0), ties Claude Opus 4.8 for the best TritonBench-G pass@1 (20.1),
 and ranks second on KernelBench L2 Fast and on CVDP. Its 61% KernelBench L1
 correctness is the highest of any model evaluated.
-A technical report describing the recipe is in preparation.
 ## Results
@@ -87,6 +88,23 @@ out = model.generate(**inputs, max_new_tokens=2048)
 print(tokenizer.decode(out[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True))
 ```
 ## License
 Apache-2.0, inherited from the base model, Qwen3.6-27B.

   <img src="figures/title.png" alt="iCoder-27B" width="420">
 </p>
+<div align="center"><a href="https://github.com/bingreeky/iCoder"><img src="https://img.shields.io/badge/GitHub-iCoder-181717?logo=github&logoColor=white" alt="GitHub"></a> <a href="https://huggingface.co/i-Coder/iCoder-27B/blob/main/Coder_Tech_Report.pdf"><img src="https://img.shields.io/badge/Technical%20Report-PDF-b68b32" alt="Technical Report"></a></div>
 iCoder-27B is a 27B-parameter model for industrial coding, covering RTL design
 and GPU kernel optimization.
 and ranks second on KernelBench L2 Fast and on CVDP. Its 61% KernelBench L1
 correctness is the highest of any model evaluated.
+The full technical report describing the recipe is available
+[here](Coder_Tech_Report.pdf).
 ## Results
 print(tokenizer.decode(out[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True))
 ```
+## Citation
+If you find iCoder useful in your work, please cite the technical report:
+```bibtex
+@techreport{yang2026icoder,
+  title     = {iCoder-27B: Recursive AI-Led Development of Frontier Industrial Coding Model},
+  author    = {Cheng Yang and Jiayang Lyu and Shangyuan Liu and Guibin Zhang and
+               Jiong Lin and Xinlei Yu and Junchi Yan and Shuicheng Yan and
+               Weinan E and Linfeng Zhang and Linfeng Zhang and Qibing Ren},
+  year      = {2026},
+  month     = aug,
+  type      = {Technical Report},
+  url       = {https://huggingface.co/i-Coder/iCoder-27B}
+}
+```
 ## License
 Apache-2.0, inherited from the base model, Qwen3.6-27B.