Instructions to use BCCard/Qwen3-32B-FP8-Dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BCCard/Qwen3-32B-FP8-Dynamic with Transformers:

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

pipe = pipeline("text-generation", model="BCCard/Qwen3-32B-FP8-Dynamic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BCCard/Qwen3-32B-FP8-Dynamic")
model = AutoModelForCausalLM.from_pretrained("BCCard/Qwen3-32B-FP8-Dynamic", 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 BCCard/Qwen3-32B-FP8-Dynamic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BCCard/Qwen3-32B-FP8-Dynamic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BCCard/Qwen3-32B-FP8-Dynamic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BCCard/Qwen3-32B-FP8-Dynamic

SGLang

How to use BCCard/Qwen3-32B-FP8-Dynamic 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 "BCCard/Qwen3-32B-FP8-Dynamic" \
    --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": "BCCard/Qwen3-32B-FP8-Dynamic",
		"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 "BCCard/Qwen3-32B-FP8-Dynamic" \
        --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": "BCCard/Qwen3-32B-FP8-Dynamic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use BCCard/Qwen3-32B-FP8-Dynamic with Docker Model Runner:
```
docker model run hf.co/BCCard/Qwen3-32B-FP8-Dynamic
```

sh2orc commited on Jun 20, 2025

Commit

2c48ccf

verified ·

1 Parent(s): 7e85a54

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -12,7 +12,7 @@ tags:
 - FP8
 ---
-# Qwen3-32B-FP8-dynamic
 ## Model Overview
 - **Model Architecture:** Qwen3ForCausalLM
@@ -30,7 +30,7 @@ tags:
 - **Out-of-scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws).
 - **Release Date:** 05/02/2025
 - **Version:** 1.0
-- **Model Developers:** RedHat (Neural Magic)
 ### Model Optimizations
@@ -51,7 +51,7 @@ This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/
 from vllm import LLM, SamplingParams
 from transformers import AutoTokenizer
-model_id = "RedHatAI/Qwen3-32B-FP8-dynamic"
 number_gpus = 1
 sampling_params = SamplingParams(temperature=0.6, top_p=0.95, top_k=20, min_p=0, max_tokens=256)
@@ -128,7 +128,7 @@ The model was evaluated on the OpenLLM leaderboard tasks (version 1), using [lm-
   ```
   lm_eval \
     --model vllm \
-    --model_args pretrained="RedHatAI/Qwen3-32B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.5,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=1 \
     --tasks openllm \
     --apply_chat_template\
     --fewshot_as_multiturn \

 - FP8
 ---
+# Qwen3-32B-FP8-Dynamic
 ## Model Overview
 - **Model Architecture:** Qwen3ForCausalLM
 - **Out-of-scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws).
 - **Release Date:** 05/02/2025
 - **Version:** 1.0
+- **Model Developers:** BC Card, Redhat
 ### Model Optimizations
 from vllm import LLM, SamplingParams
 from transformers import AutoTokenizer
+model_id = "BCCard/Qwen3-32B-FP8-dynamic"
 number_gpus = 1
 sampling_params = SamplingParams(temperature=0.6, top_p=0.95, top_k=20, min_p=0, max_tokens=256)
   ```
   lm_eval \
     --model vllm \
+    --model_args pretrained="BCCard/Qwen3-32B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.5,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=1 \
     --tasks openllm \
     --apply_chat_template\
     --fewshot_as_multiturn \