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

Libraries

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

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

pipe = pipeline("text-generation", model="axteam/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("axteam/Nanbeige4.3-33B-NVFP4")
model = AutoModelForCausalLM.from_pretrained("axteam/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 axteam/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 "axteam/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": "axteam/Nanbeige4.3-33B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

Nanbeige4.3-33B · NVFP4 (W4A4, FP4)

4-bit quantization of Nanbeige/Nanbeige4.3-33B for vLLM serving. Quantized by axteam.


Base model	`Nanbeige/Nanbeige4.3-33B`
Method	NVFP4 (W4A4, FP4)
Format	compressed-tensors `nvfp4-pack-quantized`
Weights / activations	W4A4 — FP4 (E2M1) weights group 16 + FP8 scale, FP4 activations
Architecture	Dense (Llama architecture) · 52 layers · text-only
Size on disk	~22.1 GB
Calibration	256 samples
License	apache-2.0

Quantization details

Scheme — W4A4 — FP4 (E2M1) weights group 16 + FP8 scale, FP4 activations, stored as compressed-tensors nvfp4-pack-quantized.
Kept in BF16 — token embeddings, the LM head, and all RMSNorms. Only attention & MLP projections are quantized.
Post-training quantization (no retraining). Tokenizer / chat_template identical to the original.

Evaluation (measured)

Fidelity to the BF16 original on an internal mixed EN/KO set (100 prompts).

Metric	This model	BF16 original
Perplexity (lower = closer)	1.3594	1.2232 (+11.1%)
Top-1 next-token agreement	90.2%	99.1%

⚠️ Note: noticeable 4-bit degradation; prefer 8-bit (FP8 / AWQ INT8).

Requirements


Runtime	vLLM — the architecture is in vLLM; this build not run here yet.
vLLM install	vLLM 0.32 itself needs Python 3.11–3.14, torch 2.13 (CUDA 13.0 build, so an NVIDIA driver with CUDA 13 support), transformers ≥5.16.1,<5.20 and compressed-tensors 0.17.0 (both pinned by vLLM; 0.17.0 reads this checkpoint, which was saved with 0.19.0 — do not upgrade it separately).
GPU	Full FP4 (W4A4) speed on Blackwell — B200/GB200 (sm100), B300 (sm103), RTX 50xx / RTX PRO 6000 (sm120). Turing–Hopper (sm75–90) fall back to weight-only FP4 (slower, vLLM warns). V100 (sm70) is not supported. (Kernel choice per GPU from vLLM 0.32's selection code; only B200 was run here.)
Memory	Weights: 22.1 GB. Add KV cache (grows with context length × concurrent requests) and a few GB for activations / CUDA graphs; use `--tensor-parallel-size N` when the weights do not fit one GPU.
Transformers (without vLLM)	`transformers>=4.56.0` + `compressed-tensors>=0.15.0` (same Llama architecture as MiniCPM5; not run here for Nanbeige).
trust_remote_code	not needed

Usage (vLLM)

Start an OpenAI-compatible server:

vllm serve axteam/Nanbeige4.3-33B-NVFP4 --max-model-len 32768

Query it:

curl http://localhost:8000/v1/chat/completions -H "Content-Type: application/json" -d '{
  "model": "axteam/Nanbeige4.3-33B-NVFP4",
  "messages": [{"role": "user", "content": "대한민국의 수도는 어디인가요?"}],
  "max_tokens": 512
}'

Offline inference in Python:

from vllm import LLM, SamplingParams

llm = LLM(model="axteam/Nanbeige4.3-33B-NVFP4", max_model_len=32768)
params = SamplingParams(max_tokens=1024)
out = llm.chat([{"role": "user", "content": "Explain model quantization in two sentences."}], params)
print(out[0].outputs[0].text)

Thinking mode is on by default in the chat template; to turn it off pass chat_template_kwargs={"enable_thinking": False} (Python llm.chat(..., chat_template_kwargs=...), or "chat_template_kwargs": {"enable_thinking": false} in the request body).

Reducing KV-cache memory (optional, serve-time)

The KV cache is kept in BF16 by default. KV-cache precision is a runtime choice, independent of the weight quantization above; for long contexts or large batches FP8 roughly halves KV-cache memory:

vllm serve axteam/Nanbeige4.3-33B-NVFP4 --kv-cache-dtype fp8

License

Quantized derivative of Nanbeige/Nanbeige4.3-33B (apache-2.0).

한국어 요약

Nanbeige/Nanbeige4.3-33B 를 NVFP4 (W4A4, FP4) 로 양자화한 서빙용(4-bit) 모델입니다. 작성: axteam.

방식 — 가중치·활성화 FP4(W4A4). Blackwell FP4 텐서코어. 형식 compressed-tensors nvfp4-pack-quantized.
BF16 유지 — 임베딩·LM 헤드·모든 norm. attention·MLP projection 만 양자화.
PTQ(재학습 없음), 토크나이저·chat_template 원본 동일.
품질(실측) — BF16 대비 perplexity 1.3594(원본 1.2232, +11.1%), top-1 90.2%(원본 99.1%).
⚠️ 4비트 열화 큼 — 8비트 권장.
요구사항 — vLLM; GPU FP4(W4A4) 제 속도는 Blackwell(B200·B300·RTX 50xx/PRO 6000). Turing~Hopper 는 가중치 전용 FP4 로 자동 전환(느림); 가중치 22.1 GB + KV 캐시; Transformers 직접 사용: transformers ≥4.56.0(Nanbeige 는 미실행).
실행 — vllm serve axteam/Nanbeige4.3-33B-NVFP4 --max-model-len 32768 로 OpenAI 호환 서버(포트 8000), 또는 Python LLM(model="axteam/Nanbeige4.3-33B-NVFP4").chat(...) (위 예시). thinking 끄기: chat_template_kwargs={"enable_thinking": False}.
KV 캐시 절감(런타임) — --kv-cache-dtype fp8.

Downloads last month: 70

Safetensors

Model size

20B params

Tensor type

BF16

Model tree for axteam/Nanbeige4.3-33B-NVFP4

Base model

Nanbeige/Nanbeige4.3-33B-Base

Finetuned

Nanbeige/Nanbeige4.3-33B

Quantized

(99)

this model