Instructions to use NorwAI/NorwAI-Mixtral-8x7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NorwAI/NorwAI-Mixtral-8x7B with Transformers:

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

pipe = pipeline("text-generation", model="NorwAI/NorwAI-Mixtral-8x7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NorwAI/NorwAI-Mixtral-8x7B")
model = AutoModelForCausalLM.from_pretrained("NorwAI/NorwAI-Mixtral-8x7B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use NorwAI/NorwAI-Mixtral-8x7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NorwAI/NorwAI-Mixtral-8x7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NorwAI/NorwAI-Mixtral-8x7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/NorwAI/NorwAI-Mixtral-8x7B

SGLang

How to use NorwAI/NorwAI-Mixtral-8x7B 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 "NorwAI/NorwAI-Mixtral-8x7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NorwAI/NorwAI-Mixtral-8x7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "NorwAI/NorwAI-Mixtral-8x7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NorwAI/NorwAI-Mixtral-8x7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use NorwAI/NorwAI-Mixtral-8x7B with Docker Model Runner:
```
docker model run hf.co/NorwAI/NorwAI-Mixtral-8x7B
```

Any quantized versions?

by jan-heldal-np - opened Oct 13, 2025

Discussion

jan-heldal-np

Oct 13, 2025

I notice that this version of NorwAI-Mixtral-8x7b is encoded in BF16, which is excellent for those wishing to post-train further, but impractical for us wanting to use the model as is.

Are there any quantized versions available? How much quality loss should one expect from them compared to BF16?

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