Instructions to use webbrain-one/Nanbeige4.3-33B-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use webbrain-one/Nanbeige4.3-33B-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="webbrain-one/Nanbeige4.3-33B-NVFP4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("webbrain-one/Nanbeige4.3-33B-NVFP4")
model = AutoModelForCausalLM.from_pretrained("webbrain-one/Nanbeige4.3-33B-NVFP4", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use webbrain-one/Nanbeige4.3-33B-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "webbrain-one/Nanbeige4.3-33B-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": "webbrain-one/Nanbeige4.3-33B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/webbrain-one/Nanbeige4.3-33B-NVFP4

SGLang

How to use webbrain-one/Nanbeige4.3-33B-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 "webbrain-one/Nanbeige4.3-33B-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": "webbrain-one/Nanbeige4.3-33B-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 "webbrain-one/Nanbeige4.3-33B-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": "webbrain-one/Nanbeige4.3-33B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use webbrain-one/Nanbeige4.3-33B-NVFP4 with Docker Model Runner:
```
docker model run hf.co/webbrain-one/Nanbeige4.3-33B-NVFP4
```

Nanbeige4.3-33B-NVFP4

NVFP4 quantization of Nanbeige/Nanbeige4.3-33B @ c1093c501cc6, made with llm-compressor and saved in compressed-tensors format for vLLM.

Weights and activations in FP4 (W4A4): E2M1 values in blocks of 16 with FP8 (E4M3) block scales and a per-tensor FP32 scale. Activation block scales are computed on the fly at inference.
Kept in BF16: token embeddings, lm_head, norms.
Size: 22.1 GB (BF16 original: 66.2 GB).

Quantized by WebBrain, an open-source (MIT) AI browser agent for Chrome and Firefox that reads pages, extracts data and automates tasks. It runs on this model locally through the vLLM endpoint below.

Quick quality check

Model	GSM8K, first 100 test questions, greedy, non-thinking
BF16 original	96.0%
NVFP4 (this repo)	95.0%

A small sanity check run right after quantization (vLLM 0.32.0, NVIDIA RTX PRO 6000 Blackwell Server Edition). It catches a broken quant; it is not a benchmark.

Usage

vllm serve webbrain-one/Nanbeige4.3-33B-NVFP4 \
  --enable-auto-tool-choice \
  --reasoning-parser qwen3 \
  --tool-call-parser qwen3_coder

Native FP4 tensor-core path on Blackwell GPUs (SM100 / SM120). On older GPUs vLLM runs the weights as FP4 but skips activation quantization.
On a single 32 GB card (e.g. RTX 5090), add --kv-cache-dtype fp8 --max-model-len 32768 and raise the context length based on the KV-cache size vLLM reports at startup. The full 512K context needs far more memory.
Chat template options (enable_thinking, preserve_thinking, tool_call_format) and the recommended sampling settings are the same as the original: temperature 1.0 / top_p 0.95 for agentic and tool use, 0.6 / 0.95 for reasoning and chat. See the original card for details and benchmarks.

Recipe


Scheme	`NVFP4`, all decoder `Linear` layers (364 = 52 layers x 7), `lm_head` ignored
Algorithm	round-to-nearest (`QuantizationModifier`)
Calibration	256 samples, up to 2048 tokens (mean 552), rendered with the model's chat template: `mlabonne/open-perfectblend` (256)
Tools	llm-compressor 0.14.0.1, compressed-tensors 0.19.0, transformers 5.17.0, torch 2.11.0+cu128
Hardware	NVIDIA RTX PRO 6000 Blackwell Server Edition, 3.1 min

config.json is the original config plus quantization_config; tokenizer and generation files are unchanged copies of the original.

License

Apache-2.0, same as the original model by the Nanbeige LLM Lab.

Downloads last month: 234

Safetensors

Model size

20B params

Tensor type

BF16

Model tree for webbrain-one/Nanbeige4.3-33B-NVFP4

Base model

Nanbeige/Nanbeige4.3-33B-Base

Finetuned

Nanbeige/Nanbeige4.3-33B

Quantized

(72)

this model