Instructions to use Conexis/DeepSeek-R1-0528-Channel-INT8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Conexis/DeepSeek-R1-0528-Channel-INT8 with Transformers:

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

pipe = pipeline("text-generation", model="Conexis/DeepSeek-R1-0528-Channel-INT8", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Conexis/DeepSeek-R1-0528-Channel-INT8", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Conexis/DeepSeek-R1-0528-Channel-INT8", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Conexis/DeepSeek-R1-0528-Channel-INT8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Conexis/DeepSeek-R1-0528-Channel-INT8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Conexis/DeepSeek-R1-0528-Channel-INT8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Conexis/DeepSeek-R1-0528-Channel-INT8

SGLang

How to use Conexis/DeepSeek-R1-0528-Channel-INT8 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 "Conexis/DeepSeek-R1-0528-Channel-INT8" \
    --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": "Conexis/DeepSeek-R1-0528-Channel-INT8",
		"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 "Conexis/DeepSeek-R1-0528-Channel-INT8" \
        --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": "Conexis/DeepSeek-R1-0528-Channel-INT8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Conexis/DeepSeek-R1-0528-Channel-INT8 with Docker Model Runner:
```
docker model run hf.co/Conexis/DeepSeek-R1-0528-Channel-INT8
```

Channel INT8 for Deepseek v3.1 Terminus

by Doctor-Shotgun - opened Sep 25, 2025

Discussion

Doctor-Shotgun

Sep 25, 2025

•

edited Oct 1, 2025

Hey - thanks for these! I’ve been playing with CPU inference in sglang on the Xeon backend and these are the fastest quants that are supported.

Was wondering if you had plans to upload a Channel INT8 quant of the new v3.1 Terminus model?

EDIT: Intervitens did one, no longer needed

Doctor-Shotgun changed discussion status to closed Oct 1, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment