Instructions to use useful-quants/Mistral-NeMo-Minitron-8B-Instruct-W4A16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use useful-quants/Mistral-NeMo-Minitron-8B-Instruct-W4A16 with Transformers:

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

pipe = pipeline("text-generation", model="useful-quants/Mistral-NeMo-Minitron-8B-Instruct-W4A16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("useful-quants/Mistral-NeMo-Minitron-8B-Instruct-W4A16")
model = AutoModelForCausalLM.from_pretrained("useful-quants/Mistral-NeMo-Minitron-8B-Instruct-W4A16", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use useful-quants/Mistral-NeMo-Minitron-8B-Instruct-W4A16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "useful-quants/Mistral-NeMo-Minitron-8B-Instruct-W4A16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "useful-quants/Mistral-NeMo-Minitron-8B-Instruct-W4A16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/useful-quants/Mistral-NeMo-Minitron-8B-Instruct-W4A16

SGLang

How to use useful-quants/Mistral-NeMo-Minitron-8B-Instruct-W4A16 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 "useful-quants/Mistral-NeMo-Minitron-8B-Instruct-W4A16" \
    --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": "useful-quants/Mistral-NeMo-Minitron-8B-Instruct-W4A16",
		"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 "useful-quants/Mistral-NeMo-Minitron-8B-Instruct-W4A16" \
        --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": "useful-quants/Mistral-NeMo-Minitron-8B-Instruct-W4A16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use useful-quants/Mistral-NeMo-Minitron-8B-Instruct-W4A16 with Docker Model Runner:
```
docker model run hf.co/useful-quants/Mistral-NeMo-Minitron-8B-Instruct-W4A16
```

Mistral-NeMo-Minitron-8B-Instruct W4A16

Ampere-friendly serving build of nvidia/Mistral-NeMo-Minitron-8B-Instruct. Text-side linears are compressed-tensors W4A16.

Stock proof

docker run --rm -it \
  --gpus all \
  --ipc=host \
  -p 8001:8000 \
  -v ~/.cache/huggingface:/root/.cache/huggingface \
  vllm/vllm-openai:latest \
  nvidia/Mistral-NeMo-Minitron-8B-Instruct \
  --served-model-name Mistral-NeMo-Minitron-8B-Instruct-stock \
  --dtype bfloat16 \
  --max-model-len 4096 \
  --gpu-memory-utilization 0.76

Use

docker run --rm -it \
  --gpus all \
  --ipc=host \
  -p 8001:8000 \
  -v /path/to/Mistral-NeMo-Minitron-8B-Instruct-W4A16:/model \
  -v ~/.cache/huggingface:/root/.cache/huggingface \
  vllm/vllm-openai:latest \
  --model /model \
  --served-model-name Mistral-NeMo-Minitron-8B-Instruct-W4A16 \
  --dtype bfloat16 \
  --quantization compressed-tensors \
  --max-model-len 4096

Smoke test

python verify.py --url http://localhost:8001/v1/completions

Notes

Best fit: RTX 30xx/40xx Ampere cards.
The repo includes the calibration corpus used for verification.

Downloads last month: 12

Safetensors

Model size

8B params

Tensor type

I64

I32

BF16

Model tree for useful-quants/Mistral-NeMo-Minitron-8B-Instruct-W4A16

Base model

nvidia/Mistral-NeMo-Minitron-8B-Base

Finetuned

nvidia/Mistral-NeMo-Minitron-8B-Instruct

Quantized

(13)

this model