Instructions to use axteam/Qwen3.5-4B-AWQ-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use axteam/Qwen3.5-4B-AWQ-4bit with Transformers:

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

pipe = pipeline("image-text-to-text", model="axteam/Qwen3.5-4B-AWQ-4bit")
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/Qwen3.5-4B-AWQ-4bit")
model = AutoModelForMultimodalLM.from_pretrained("axteam/Qwen3.5-4B-AWQ-4bit", 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/Qwen3.5-4B-AWQ-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "axteam/Qwen3.5-4B-AWQ-4bit"
# 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/Qwen3.5-4B-AWQ-4bit",
		"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/Qwen3.5-4B-AWQ-4bit

SGLang

How to use axteam/Qwen3.5-4B-AWQ-4bit 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/Qwen3.5-4B-AWQ-4bit" \
    --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/Qwen3.5-4B-AWQ-4bit",
		"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/Qwen3.5-4B-AWQ-4bit" \
        --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/Qwen3.5-4B-AWQ-4bit",
		"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/Qwen3.5-4B-AWQ-4bit with Docker Model Runner:
```
docker model run hf.co/axteam/Qwen3.5-4B-AWQ-4bit
```

Qwen3.5-4B · AWQ INT4 (W4A16)

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

Revision 2026-11-01: un-smoothed RMSNorm weights restored bit-exactly from the original. llm-compressor's offset-norm handling had left BF16 rounding noise (at most 0.4% in the effective gain) in the norms that AWQ does not smooth. Quantized weights and the AWQ-smoothed norms are unchanged. The measurements on this card were taken before this change.


Base model	`Qwen/Qwen3.5-4B`
Method	AWQ INT4 (W4A16)
Format	compressed-tensors `pack-quantized`
Weights / activations	W4A16 — INT4 asymmetric weights, group size 32 (BF16 scale + INT4 zero-point), BF16 activations
Architecture	Hybrid (linear-attention + full-attention) · Dense · multimodal (vision) · MTP head
Size on disk	~4.2 GB
Calibration	256 samples (Korean-heavy mixed corpus)
License	Apache-2.0

Quantization details

Scheme — W4A16 — INT4 asymmetric weights, group size 32 (BF16 scale + INT4 zero-point), BF16 activations, stored as compressed-tensors 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 SSM non-linear parts (linear_attn.conv1d/A_log/dt_bias). Left unquantized to preserve quality (about 21% of all parameters in this build).
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. AWQ uses a small calibration set (no gradient) to protect salient weight channels before rounding.

Benchmarks (measured)

Every column was measured with the same harness and settings — lm-evaluation-harness on vLLM, greedy, few-shot completion (no chat template). Percentages are recovery vs. the BF16 original.

Benchmark	BF16 (original)	FP8-dynamic	AWQ-8bit	NVFP4A16	NVFP4	AWQ-4bit (this repo)
MMLU (5-shot)	55.18	57.99 (105.1%)	54.79 (99.3%)	60.58 (109.8%)	58.61 (106.2%)	60.89 (110.3%)
GSM8K (5-shot, strict)	74.07	73.92 (99.8%)	73.84 (99.7%)	76.72 (103.6%)	73.31 (99.0%)	76.42 (103.2%)
ARC-Challenge (0-shot)	54.61	53.92 (98.8%)	54.52 (99.8%)	54.86 (100.5%)	53.92 (98.8%)	54.35 (99.5%)
Winogrande (5-shot)	68.75	67.96 (98.9%)	69.14 (100.6%)	68.90 (100.2%)	69.38 (100.9%)	68.90 (100.2%)
KMMLU (5-shot, direct)	50.47	50.13 (99.3%)	50.48 (100.0%)	51.49 (102.0%)	50.26 (99.6%)	49.02 (97.1%)
HAE-RAE (0-shot)	62.42	61.50 (98.5%)	62.05 (99.4%)	61.69 (98.8%)	59.76 (95.7%)	58.48 (93.7%)
Average	60.92	60.90 (100.0%)	60.81 (99.8%)	62.37 (102.4%)	60.87 (99.9%)	61.34 (100.7%)

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)	1.6672	1.5703 (+6.2%)
Top-1 next-token agreement	89.0%	99.2%

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

Requirements


Runtime	vLLM — the architecture is in vLLM ≥ 0.17.0; tested here with vLLM 0.32.0.
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	NVIDIA Turing (sm75) or newer — weight-only INT, no special tensor cores needed. V100 (sm70) is not supported. (Kernel choice per GPU from vLLM 0.32's selection code; only B200 was run here.)
Memory	Weights: 4.2 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>=5.2.0` + `compressed-tensors>=0.15.0` (checked on CPU with Qwen3.5-0.8B FP8 / AWQ-4bit / NVFP4A16 / NVFP4).
trust_remote_code	not needed

Usage (vLLM)

Start an OpenAI-compatible server:

vllm serve axteam/Qwen3.5-4B-AWQ-4bit --max-model-len 32768

Query it:

curl http://localhost:8000/v1/chat/completions -H "Content-Type: application/json" -d '{
  "model": "axteam/Qwen3.5-4B-AWQ-4bit",
  "messages": [{"role": "user", "content": "대한민국의 수도는 어디인가요?"}],
  "max_tokens": 512
}'

Offline inference in Python:

from vllm import LLM, SamplingParams

llm = LLM(model="axteam/Qwen3.5-4B-AWQ-4bit", 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)

# image input (URL or data: URI)
messages = [{"role": "user", "content": [
    {"type": "image_url", "image_url": {"url": "https://example.com/your-image.png"}},
    {"type": "text", "text": "Describe this image."},
]}]
out = llm.chat(messages, 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). Text-only serving: add --limit-mm-per-prompt '{"image": 0, "video": 0}' to skip loading the vision encoder's memory budget.

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/Qwen3.5-4B-AWQ-4bit --kv-cache-dtype fp8

License

Quantized derivative of Qwen/Qwen3.5-4B (Apache-2.0). All original weights, tokenizer and chat template belong to the Qwen team.

한국어 요약

Qwen/Qwen3.5-4B의 AWQ INT4 (W4A16) 양자화 빌드 · 제작 axteam

개요

항목	내용
원본 모델	`Qwen/Qwen3.5-4B`
양자화 방식	AWQ INT4 (W4A16)
저장 형식	compressed-tensors `pack-quantized`
모델 구조	하이브리드 어텐션(선형 어텐션 + 풀 어텐션) · Dense · 멀티모달(비전) · MTP 헤드
용량	약 4.2 GB
보정 데이터	샘플 256개 (한국어 위주 혼합 코퍼스)

양자화 상세

가중치: INT4 비대칭, 그룹 크기 32 (BF16 스케일 + INT4 영점)
활성화: BF16 (양자화하지 않음)
양자화 절차: PTQ(학습 후 양자화, 재학습 없음), AWQ 방식 — 보정 데이터로 활성화가 큰 가중치 채널을 찾아 채널별 스케일로 보호한 뒤 INT4로 반올림
BF16 유지: 비전 타워·투영층(model.visual.*), MTP 헤드(mtp.*), 모든 RMSNorm, 토큰 임베딩, LM 헤드, SSM의 선형층 외 파라미터(linear_attn.conv1d·A_log·dt_bias) — 전체 파라미터의 약 21%
원본 파일: 토크나이저·chat template·generation config는 원본과 동일, config.json은 원본에 quantization_config 블록만 추가

품질 (실측)

원본 대비 충실도: PPL 1.6672 (원본 1.5703, +6.2%, 낮을수록 원본에 가까움), 다음 토큰 top-1 일치율 89.0% (원본 자체 기준값 99.2%) — 내부 영어·한국어 혼합 프롬프트 100개, 원본(BF16)의 greedy 답변을 기준 텍스트로 측정
벤치마크 평균: 61.34 (원본 60.92, 100.7%) — MMLU·GSM8K·ARC-Challenge·Winogrande·KMMLU·HAE-RAE 6종 평균, lm-evaluation-harness + vLLM, chat template 없는 few-shot·greedy, 모든 빌드를 같은 설정으로 측정
한국어 벤치마크: KMMLU 49.02 (원본 50.47, 97.1%) · HAE-RAE 58.48 (원본 62.42, 93.7%)

요구사항

실행 엔진: vLLM 0.17.0 이상(이 구조를 지원하는 첫 버전), 이 빌드는 vLLM 0.32.0에서 실행 확인
vLLM 0.32 설치 조건: Python 3.11~3.14, torch 2.13(CUDA 13.0 빌드, CUDA 13 지원 드라이버 필요), transformers 5.16.1 이상 5.20 미만, compressed-tensors 0.17.0 — transformers·compressed-tensors는 vLLM이 버전을 고정하므로 compressed-tensors를 따로 업그레이드하지 말 것 (이 체크포인트는 0.19.0으로 저장됐지만 0.17.0에서도 로드됨)
GPU: NVIDIA Turing(sm75) 이상, V100(sm70) 미지원 — 가중치 전용 정수 형식이라 FP8·FP4 전용 텐서코어 불필요 (GPU별 지원 여부는 vLLM 0.32 커널 선택 코드 기준, 실제 실행은 B200에서만 확인)
메모리: 가중치 4.2 GB + KV 캐시(컨텍스트 길이 × 동시 요청 수에 비례) + 활성화·CUDA graph용 수 GB — GPU 한 장에 다 들어가지 않으면 --tensor-parallel-size N으로 분산
Transformers로 직접 사용: transformers 5.2.0 이상 + compressed-tensors 0.15.0 이상 (Qwen3.5-0.8B의 FP8·AWQ-4bit·NVFP4A16·NVFP4 빌드로 CPU에서 확인)
trust_remote_code: 불필요

사용법

서버 실행: vllm serve axteam/Qwen3.5-4B-AWQ-4bit --max-model-len 32768 — OpenAI 호환 API
Python: LLM(model="axteam/Qwen3.5-4B-AWQ-4bit", max_model_len=32768).chat(...) — 전체 예시는 위 영어 본문 'Usage (vLLM)' 절 참고
thinking 모드: 기본 켜짐 — 끄려면 chat_template_kwargs={"enable_thinking": False} 전달(Python은 llm.chat() 인자, HTTP는 요청 본문의 "chat_template_kwargs": {"enable_thinking": false})
이미지 입력: 메시지에 image_url 항목 사용
텍스트만 사용할 때: --limit-mm-per-prompt '{"image": 0, "video": 0}' — 비전 타워용 메모리 예약을 생략해 메모리 절약
KV 캐시 절감(선택): vllm serve에 --kv-cache-dtype fp8 추가 — 기본 BF16인 KV 캐시를 FP8로 저장해 KV 캐시 메모리를 약 절반으로 줄임 (긴 컨텍스트·동시 요청이 많을 때 유리, 가중치 양자화와 별개인 실행 옵션)

참고

수정 이력 (2026-11-01): AWQ가 스무딩하지 않는 RMSNorm 가중치를 원본과 비트 단위로 같게 복원 — llm-compressor가 남긴 BF16 반올림 오차(실효 가중치 기준 최대 0.4%) 제거, 양자화 가중치와 AWQ로 스무딩된 RMSNorm은 변경 없음, 품질 항목의 측정값은 복원 전 기준