Instructions to use EliovpAI/Qwen3-0.6B-FP8-KV with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EliovpAI/Qwen3-0.6B-FP8-KV with Transformers:

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

pipe = pipeline("text-generation", model="EliovpAI/Qwen3-0.6B-FP8-KV")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EliovpAI/Qwen3-0.6B-FP8-KV")
model = AutoModelForCausalLM.from_pretrained("EliovpAI/Qwen3-0.6B-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/Qwen3-0.6B-FP8-KV with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EliovpAI/Qwen3-0.6B-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/Qwen3-0.6B-FP8-KV",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/EliovpAI/Qwen3-0.6B-FP8-KV

SGLang

How to use EliovpAI/Qwen3-0.6B-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/Qwen3-0.6B-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/Qwen3-0.6B-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/Qwen3-0.6B-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/Qwen3-0.6B-FP8-KV",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use EliovpAI/Qwen3-0.6B-FP8-KV with Docker Model Runner:
```
docker model run hf.co/EliovpAI/Qwen3-0.6B-FP8-KV
```

Eliovp commited on Aug 2, 2025

Commit

7906db9

verified ·

1 Parent(s): 275c832

Create README.md

Browse files

Files changed (1) hide show

README.md +48 -0

README.md ADDED Viewed

	@@ -0,0 +1,48 @@

+---
+base_model:
+- Qwen/Qwen3-0.6B
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- FP8
+- OCP
+- AMD
+- ROCM
+- Quark
+- vllm
+---
+# Qwen3-0.6B-FP8-KV
+> **Lightweight OCP FP8_e4m3 quant of Qwen3-0.6B** with end-to-end KV-cache FP8 support, built with AMD Quark for ROCm.
+## Introduction
+Qwen3-0.6B-FP8-KV is an OCP-standard FP8_e4m3 quantization of [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B),
+produced with **AMD Quark**.
+## Quantization Strategy
+- **Quantizer**: AMD Quark v0.9+
+- **Numeric Format**: OCP FP8_e4m3, symmetric per-tensor
+- **Scope**: All `Linear` layers (excl. `lm_head`), activations **and the KV cache**
+- **Block Size**: 128 (OCP-aligned)
+- **Calibration**: 128 Pile samples
+- **Metadata**: scales & block info in JSON; weights in SafeTensors
+## Performance Snapshot
+| Metric                 | FP16 Baseline | FP8_e4m3 Quantized |
+|------------------------|--------------:|-------------------:|
+| Wikitext2 Perplexity   |        ~22.1  |             ~25.8  |
+| Memory Footprint       |         1.0×  |             0.50×  |
+| Inference Throughput   |         1.0×  |             1.3×   |
+## Evaluation
+We measured perplexity on WikiText2:
+- FP16 (Qwen3-0.6B)             →  22.1 PPL
+- FP8_e4m3 (this model)         →  25.8 PPL
+## License
+This model inherits the Qwen3-0.6B license.