Instructions to use EliovpAI/Qwen3-14B-FP8-KV with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EliovpAI/Qwen3-14B-FP8-KV with Transformers:

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

pipe = pipeline("text-generation", model="EliovpAI/Qwen3-14B-FP8-KV")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EliovpAI/Qwen3-14B-FP8-KV")
model = AutoModelForCausalLM.from_pretrained("EliovpAI/Qwen3-14B-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/Qwen3-14B-FP8-KV with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EliovpAI/Qwen3-14B-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/Qwen3-14B-FP8-KV",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/EliovpAI/Qwen3-14B-FP8-KV

SGLang

How to use EliovpAI/Qwen3-14B-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/Qwen3-14B-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/Qwen3-14B-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/Qwen3-14B-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/Qwen3-14B-FP8-KV",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use EliovpAI/Qwen3-14B-FP8-KV with Docker Model Runner:
```
docker model run hf.co/EliovpAI/Qwen3-14B-FP8-KV
```

Qwen3-14B-FP8-KV

Enterprise-grade OCP FP8 quantized Qwen-3 14B for AMD ROCm, end-to-end KV-cache in FP8 with Quark

Introduction

Qwen3-14B-FP8-KV is a full-pipeline, OCP-compliant FP8_e4m3 quant of Qwen/Qwen3-14B, built with AMD Quark and optimized for AMD Instinct GPUs. This model delivers ~1.8× memory savings and throughput boost vs. FP16, with only a nominal perplexity uplift (≈8.7 PPL on WikiText2).

Quantization Strategy

Quantizer: AMD Quark v0.9+
Numeric Format: OCP FP8_e4m3 symmetric, per-tensor
Scope: All Linear layers (excluding lm_head), activations, and KV cache
Group Size: 128 (block-aligned)
Calibration: 128 Pile samples (default)
Metadata: scales embedded in JSON + SafeTensors

Performance Snapshot

Metric	FP16 Baseline	FP8_e4m3 Quantized
Wikitext2 Perplexity	6.38	8.73
Memory Footprint	1.0×	0.56×

Quick Start

Serve with vLLM

Override model’s context:

export VLLM_ALLOW_LONG_MAX_MODEL_LEN=1

Serve

HIP_VISIBLE_DEVICES=0
vllm serve EliovpAI/Qwen3-14B-FP8-KV
--kv-cache-dtype fp8
----num-scheduler-steps 10 .. other arguments

Benchmark

python3 /vllm/benchmarks/benchmark_serving.py
--backend vllm
--model EliovpAI/Qwen3-14B-FP8-KV
--dataset-name sharegpt
--dataset-path /vllm/ShareGPT_V3_unfiltered_cleaned_split.json
--num-prompts 32
--random-range-ratio 1.0
--percentile-metrics ttft,tpot,itl,e2el
--sharegpt-output-len 256

Evaluation

We benchmarked on WikiText2 using vLLM’s /v1/completions PPL metric:

FP16 (Qwen3-14B) → 6.38 PPL
FP8_e4m3 (this model) → 8.73 PPL

The ~2.3-point PPL delta yields massive ROI in memory and speed—with virtually imperceptible quality loss in most benchmarks.

License

This model reuses the Qwen3-14B license.

Downloads last month: 25

Safetensors

Model size

15B params

Tensor type

BF16

F8_E4M3

Model tree for EliovpAI/Qwen3-14B-FP8-KV

Base model

Qwen/Qwen3-14B-Base

Finetuned

Qwen/Qwen3-14B

Quantized

(178)

this model