Instructions to use axteam/Qwen3.5-2B-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use axteam/Qwen3.5-2B-NVFP4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="axteam/Qwen3.5-2B-NVFP4")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("axteam/Qwen3.5-2B-NVFP4")
model = AutoModelForMultimodalLM.from_pretrained("axteam/Qwen3.5-2B-NVFP4", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use axteam/Qwen3.5-2B-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "axteam/Qwen3.5-2B-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/Qwen3.5-2B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/axteam/Qwen3.5-2B-NVFP4

SGLang

How to use axteam/Qwen3.5-2B-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/Qwen3.5-2B-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/Qwen3.5-2B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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/Qwen3.5-2B-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/Qwen3.5-2B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use axteam/Qwen3.5-2B-NVFP4 with Docker Model Runner:
```
docker model run hf.co/axteam/Qwen3.5-2B-NVFP4
```

Qwen3.5-2B · NVFP4 (W4A4, FP4)

4-bit quantization of Qwen/Qwen3.5-2B, produced for efficient vLLM serving. Quantized by axteam.


Base model	`Qwen/Qwen3.5-2B`
Method	NVFP4 (W4A4, FP4)
Format	compressed-tensors `nvfp4-pack-quantized`
Weights / activations	W4A4 — FP4 (E2M1) weights group 16 (FP8 E4M3 scale + per-tensor FP32 global scale), FP4 activations
Architecture	Hybrid (linear-attention + full-attention) · Dense · multimodal (vision) · MTP head
Size on disk	~2.9 GB
Calibration	256 samples (Korean-heavy mixed corpus)
License	Apache-2.0

Quantization details

Scheme — W4A4 — FP4 (E2M1) weights group 16 (FP8 E4M3 scale + per-tensor FP32 global scale), FP4 activations, stored as compressed-tensors nvfp4-pack-quantized.
Kept in BF16 — the vision tower & projector (model.visual.*), the multi-token-prediction head (mtp.*), all RMSNorms, token embeddings, the LM head, the entire linear-attention (GatedDeltaNet/SSM) path — FP4 is too coarse for the SSM weights, so the full linear_attn.* stays BF16. Left unquantized to preserve quality (a small fraction of parameters).
Tokenizer / chat_template / generation_config are identical to the original. config.json is the original plus a quantization_config block.

This is post-training quantization (PTQ) — no retraining, so behaviour stays faithful to the original. AWQ uses a small calibration set (no gradient) to protect salient weight channels before rounding.

Evaluation (measured)

Fidelity to the BF16 original on an internal mixed English/Korean set (100 prompts, BF16 greedy answers scored under each build — same harness for every row).

Metric	This model	BF16 original
Perplexity (lower = closer)	2.0399	1.8515 (+10.2%)
Top-1 next-token agreement	85.8%	98.9%

These measure fidelity to the base model, not absolute task scores.

⚠️ Note: this sparse-MoE model is sensitive to 4-bit quantization (+10.2% perplexity here). For production we recommend the 8-bit builds (FP8 or AWQ INT8) of this model.

Usage (vLLM)

vllm serve axteam/Qwen3.5-2B-NVFP4

Recommended sampling (Qwen): temperature=0.7, top_p=0.8, top_k=20. This is a Blackwell-only format — it needs FP4 tensor cores (B200) for full speed.

License

Quantized derivative of Qwen/Qwen3.5-2B (Apache-2.0). All original weights, tokenizer and chat template belong to the Qwen team.

한국어 요약

Qwen/Qwen3.5-2B 를 NVFP4 (W4A4, FP4) 로 양자화한 서빙용(4-bit) 모델입니다. 작성: axteam.

방식 — 가중치·활성화 모두 FP4(W4A4). Blackwell(B200) FP4 텐서코어에서 제 속도. 품질 우선이면 NVFP4A16 권장. 형식 compressed-tensors nvfp4-pack-quantized.
BF16 유지 — 비전 타워·MTP 헤드·모든 norm·임베딩/LM 헤드·SSM(linear_attn) 경로 전체(FP4가 SSM 가중치엔 너무 거칠어서).
PTQ — 재학습 없음, 원본 동작 유지.
품질(실측) — BF16 원본 대비 perplexity 2.0399(원본 1.8515, +10.2%), top-1 일치도 85.8%(원본 98.9%). 내부 영/한 100문항, 같은 하네스.
⚠️ 주의 — 이 초희소 MoE 는 4비트에 민감합니다(여기 +10.2%). 실서비스에는 8비트(FP8 또는 AWQ INT8) 빌드를 권장합니다.
사용 — vllm serve axteam/Qwen3.5-2B-NVFP4, 권장 샘플링 temperature=0.7, top_p=0.8, top_k=20.
라이선스 — 원본 Apache-2.0 파생물. 가중치·토크나이저·chat_template 권리는 Qwen 팀.