Instructions to use RedHatAI/Qwen3.8-2.4T-A95B-NVFP4-REAP-50 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/Qwen3.8-2.4T-A95B-NVFP4-REAP-50 with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/Qwen3.8-2.4T-A95B-NVFP4-REAP-50")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RedHatAI/Qwen3.8-2.4T-A95B-NVFP4-REAP-50")
model = AutoModelForCausalLM.from_pretrained("RedHatAI/Qwen3.8-2.4T-A95B-NVFP4-REAP-50", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RedHatAI/Qwen3.8-2.4T-A95B-NVFP4-REAP-50 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/Qwen3.8-2.4T-A95B-NVFP4-REAP-50"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Qwen3.8-2.4T-A95B-NVFP4-REAP-50",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RedHatAI/Qwen3.8-2.4T-A95B-NVFP4-REAP-50

SGLang

How to use RedHatAI/Qwen3.8-2.4T-A95B-NVFP4-REAP-50 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 "RedHatAI/Qwen3.8-2.4T-A95B-NVFP4-REAP-50" \
    --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": "RedHatAI/Qwen3.8-2.4T-A95B-NVFP4-REAP-50",
		"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 "RedHatAI/Qwen3.8-2.4T-A95B-NVFP4-REAP-50" \
        --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": "RedHatAI/Qwen3.8-2.4T-A95B-NVFP4-REAP-50",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RedHatAI/Qwen3.8-2.4T-A95B-NVFP4-REAP-50 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/Qwen3.8-2.4T-A95B-NVFP4-REAP-50
```

Qwen3.8-2.4T-A95B-NVFP4-REAP-50

Model Overview

Model Architecture: Qwen3_5MoeForCausalLM
- Input: Text
- Output: Text
Model Optimizations:
- Weight quantization: FP4
- Activation quantization: FP4
- Expert pruning: 50% REAP Pruning
Release Date: 2026-08-19
Version: 1.0
Model Developers: RedHatAI

This model is a quantized version of Qwen/Qwen3.8-2.4T-A95B. It was evaluated on several tasks to assess its quality in comparison to the unquantized model.

Model Optimizations

This model was obtained by applying mixed-precision quantization to Qwen/Qwen3.8-2.4T-A95B with 50% REAP Pruning of the experts: the MoE expert linear layers use FP4 (NVFP4) weights and activations, ready for inference with vLLM. Attention and non-quantized layers keep their original precision.

This optimization reduces the number of bits per parameter in the quantized MoE layers from 16 to 4, and applies 50% REAP Pruning to the experts, reducing the disk size and GPU memory requirements of those layers by approximately 75% plus the sparsity gain.

Only the weights and activations of the linear operators in the MoE experts are quantized using LLM Compressor.

Deployment

vLLM Serving

vllm serve RedHatAI/Qwen3.8-2.4T-A95B-NVFP4-REAP-50 \
    --tensor-parallel-size 8 \
    --enable-expert-parallel \
    --reasoning-parser qwen3

Creation

This model was created by applying LLM Compressor with the NVFP4 scheme and 25% REAP Pruning of the experts, exported in compressed-tensors

Downloads last month: 1,193

Safetensors

Model size

1.3T params

Tensor type

BF16

Model tree for RedHatAI/Qwen3.8-2.4T-A95B-NVFP4-REAP-50

Base model

Qwen/Qwen3.8-2.4T-A95B

Quantized

(32)

this model