Instructions to use EliovpAI/Qwen3-8B-FP8-KV with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EliovpAI/Qwen3-8B-FP8-KV with Transformers:

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

pipe = pipeline("text-generation", model="EliovpAI/Qwen3-8B-FP8-KV")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EliovpAI/Qwen3-8B-FP8-KV")
model = AutoModelForCausalLM.from_pretrained("EliovpAI/Qwen3-8B-FP8-KV")
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

vLLM

How to use EliovpAI/Qwen3-8B-FP8-KV with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EliovpAI/Qwen3-8B-FP8-KV"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EliovpAI/Qwen3-8B-FP8-KV",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/EliovpAI/Qwen3-8B-FP8-KV

SGLang

How to use EliovpAI/Qwen3-8B-FP8-KV 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 "EliovpAI/Qwen3-8B-FP8-KV" \
    --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": "EliovpAI/Qwen3-8B-FP8-KV",
		"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 "EliovpAI/Qwen3-8B-FP8-KV" \
        --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": "EliovpAI/Qwen3-8B-FP8-KV",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use EliovpAI/Qwen3-8B-FP8-KV with Docker Model Runner:
```
docker model run hf.co/EliovpAI/Qwen3-8B-FP8-KV
```

Qwen3-8B-FP8-KV

Introduction

This model was built by applying Quark with calibration samples from Pile dataset to Qwen/Qwen3-8B.

Quantization Strategy

Quantized Layers: All linear layers excluding "lm_head", ".mlp.experts."
Weight: FP8 symmetric per-tensor
Activation: FP8 symmetric per-tensor
KV Cache: FP8 symmetric per-tensor

Deployment

Quark has its own export format and allows FP8 quantized models to be efficiently deployed using the vLLM backend (vLLM-compatible).

Evaluation

Quark currently uses perplexity (PPL) as the evaluation metric for accuracy loss before and after quantization. The specific PPL algorithm can be referenced in the quantize_quark.py. The quantization evaluation results are conducted in pseudo-quantization mode, which may slightly differ from the actual quantized inference accuracy. These results are provided for reference only.

Evaluation scores

Benchmark	Qwen3-8B	Qwen3-8B-FP8-KV (this model)
Perplexity-wikitext2	9.531	9.708

Performance Summary

Accuracy Retention: 98.15% (only 1.85% perplexity increase)
Model Size: ~42% reduction vs FP16
Memory Efficiency: FP8 KV-cache for extended context
Hardware Optimization: AMD ROCm/HIP optimized

License

Based on Qwen3-8B licensing terms.

Downloads last month: 10

Safetensors

Model size

8B params

Tensor type

BF16

F8_E4M3

Model tree for EliovpAI/Qwen3-8B-FP8-KV

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Quantized

(282)

this model