Instructions to use osoleve/Qwen3.5-9B-Base-Text-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use osoleve/Qwen3.5-9B-Base-Text-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="osoleve/Qwen3.5-9B-Base-Text-NVFP4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("osoleve/Qwen3.5-9B-Base-Text-NVFP4")
model = AutoModelForCausalLM.from_pretrained("osoleve/Qwen3.5-9B-Base-Text-NVFP4")
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 osoleve/Qwen3.5-9B-Base-Text-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "osoleve/Qwen3.5-9B-Base-Text-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "osoleve/Qwen3.5-9B-Base-Text-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/osoleve/Qwen3.5-9B-Base-Text-NVFP4

SGLang

How to use osoleve/Qwen3.5-9B-Base-Text-NVFP4 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 "osoleve/Qwen3.5-9B-Base-Text-NVFP4" \
    --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": "osoleve/Qwen3.5-9B-Base-Text-NVFP4",
		"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 "osoleve/Qwen3.5-9B-Base-Text-NVFP4" \
        --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": "osoleve/Qwen3.5-9B-Base-Text-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use osoleve/Qwen3.5-9B-Base-Text-NVFP4 with Docker Model Runner:
```
docker model run hf.co/osoleve/Qwen3.5-9B-Base-Text-NVFP4
```

Qwen3.5-9B-Base-NVFP4

NVFP4 (4-bit floating point) quantization of Qwen/Qwen3.5-9B-Base using NVIDIA TensorRT Model Optimizer (modelopt).

Details

Property	Value
Base model	Qwen/Qwen3.5-9B-Base
Parameters	9.5B
Quantization	NVFP4 (group_size=16)
Model size	8.0 GB
Compression	~1.4x vs bf16
Excluded	lm_head
Producer	modelopt 0.37.0
Calibration	256 samples, CNN/DailyMail, max_seq_len=2048

Architecture

Hybrid Gated DeltaNet + Gated Attention with 32 layers in a repeating 3x linear_attention + 1x full_attention pattern. Includes MTP (Multi-Token Prediction) head.

Usage with vLLM

vllm serve Qwen3.5-9B-Base-NVFP4 \
    --quantization modelopt \
    --language-model-only \
    --trust-remote-code \
    --gpu-memory-utilization 0.85

Note: --language-model-only is required because Qwen3.5 models use ForConditionalGeneration (multimodal architecture). This flag skips the vision encoder for text-only inference.

Quantization

Produced on NVIDIA DGX Spark (GB10 Grace Blackwell, 128GB unified memory):

python quantize_nvfp4.py \
    --model Qwen/Qwen3.5-9B-Base \
    --output Qwen3.5-9B-Base-NVFP4 \
    --calib-size 256

Downloads last month: 203

Safetensors

Model size

6B params

Tensor type

BF16

F8_E4M3

Model tree for osoleve/Qwen3.5-9B-Base-Text-NVFP4

Base model

Qwen/Qwen3.5-9B-Base

Quantized

(28)

this model