--- title: Qwen2.5-VL-3B-Instruct-quantized.w8a8 canonical_url: "https://www.modelscope.cn/models/nm-testing/Qwen2.5-VL-3B-Instruct-quantized.w8a8" md_url: "https://www.modelscope.cn/models/nm-testing/Qwen2.5-VL-3B-Instruct-quantized.w8a8.md" repository: nm-testing/Qwen2.5-VL-3B-Instruct-quantized.w8a8 last_updated: 2025-05-01 license: apache-2.0 model_type: - qwen2_5_vl architectures: - Qwen2_5_VLForConditionalGeneration base_model: - Qwen/Qwen2.5-VL-3B-Instruct base_model_relation: quantized parameters: 4.1B tensor_type: - I8 - BF16 library_name: - pytorch - transformer - safetensors frameworks: - pytorch language: - en inference_backends: - "deploy_task vlm/text/emb" - "lmdeploy 0.9.1" - "sglang 0.5.2" - "vllm 0.9.2" downloads: 1895 stars: 0 tags: - vllm - vision - w8a8 --- # Qwen2.5-VL-3B-Instruct-quantized.w8a8 > Qwen2.5-VL-3B-Instruct-quantized.w8a8 - nm-testing 在 ModelScope 开源的模型。Qwen2.5-VL-3B-Instruct-quantized-w8a8 nm-testing/Qwen2.5-VL-3B-Instruct-quantized.w8a8 是 ModelScope 魔搭社区上的 4.1B 参数机器学习模型，采用 apache-2.0 许可，基于 Qwen/Qwen2.5-VL-3B-Instruct 构建，可用 deploy_task vlm/text/emb、lmdeploy 0.9.1、sglang 0.5.2 部署。 - **Repository**: nm-testing/Qwen2.5-VL-3B-Instruct-quantized.w8a8 - **License**: apache-2.0 - **Parameters**: 4.1B - **Base model**: Qwen/Qwen2.5-VL-3B-Instruct - **Inference backends**: deploy_task vlm/text/emb, lmdeploy 0.9.1, sglang 0.5.2, vllm 0.9.2 - **Tags**: vllm, vision, w8a8 - **Downloads**: 1895 - **Stars**: 0 - **Last updated**: 2025-05-01 Source: https://www.modelscope.cn/models/nm-testing/Qwen2.5-VL-3B-Instruct-quantized.w8a8 --- # Qwen2.5-VL-3B-Instruct-quantized-w8a8 ## Model Overview - **Model Architecture:** Qwen/Qwen2.5-VL-3B-Instruct - **Input:** Vision-Text - **Output:** Text - **Model Optimizations:** - **Weight quantization:** INT8 - **Activation quantization:** INT8 - **Release Date:** 2/24/2025 - **Version:** 1.0 - **Model Developers:** Neural Magic Quantized version of [Qwen/Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct). ### Model Optimizations This model was obtained by quantizing the weights of [Qwen/Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct) to INT8 data type, ready for inference with vLLM >= 0.5.2. ## Deployment ### Use with vLLM This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend, as shown in the example below. ```python from vllm.assets.image import ImageAsset from vllm import LLM, SamplingParams # prepare model llm = LLM( model="neuralmagic/Qwen2.5-VL-3B-Instruct-quantized.w8a8", trust_remote_code=True, max_model_len=4096, max_num_seqs=2, ) # prepare inputs question = "What is the content of this image?" inputs = { "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n", "multi_modal_data": { "image": ImageAsset("cherry_blossom").pil_image.convert("RGB") }, } # generate response print("========== SAMPLE GENERATION ==============") outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64)) print(f"PROMPT : {outputs[0].prompt}") print(f"RESPONSE: {outputs[0].outputs[0].text}") print("==========================================") ``` vLLM also supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details. ## Creation This model was created with [llm-compressor](https://github.com/vllm-project/llm-compressor) by running the code snippet below as part a multimodal announcement blog.
Model Creation Code ```python import base64 from io import BytesIO import torch from datasets import load_dataset from qwen_vl_utils import process_vision_info from transformers import AutoProcessor from llmcompressor.modifiers.quantization import GPTQModifier from llmcompressor.transformers import oneshot from llmcompressor.transformers.tracing import ( TraceableQwen2_5_VLForConditionalGeneration, ) # Load model. model_id = args["model_id"] model = TraceableQwen2_5_VLForConditionalGeneration.from_pretrained( model_id, device_map="auto", torch_dtype="auto", ) processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True) # Oneshot arguments DATASET_ID = "lmms-lab/flickr30k" DATASET_SPLIT = {"calibration": "test[:512]"} NUM_CALIBRATION_SAMPLES = 512 MAX_SEQUENCE_LENGTH = 2048 # Load dataset and preprocess. ds = load_dataset(DATASET_ID, split=DATASET_SPLIT) ds = ds.shuffle(seed=42) dampening_frac=args["dampening_frac"] save_name = f"{model_id.split('/')[1]}-W8A8-samples{NUM_CALIBRATION_SAMPLES}-df{dampening_frac}" save_path = os.path.join(args["save_dir"], save_name) print("Save Path will be:", save_path) # Apply chat template and tokenize inputs. def preprocess_and_tokenize(example): # preprocess buffered = BytesIO() example["image"].save(buffered, format="PNG") encoded_image = base64.b64encode(buffered.getvalue()) encoded_image_text = encoded_image.decode("utf-8") base64_qwen = f"data:image;base64,{encoded_image_text}" messages = [ { "role": "user", "content": [ {"type": "image", "image": base64_qwen}, {"type": "text", "text": "What does the image show?"}, ], } ] text = processor.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) image_inputs, video_inputs = process_vision_info(messages) # tokenize return processor( text=[text], images=image_inputs, videos=video_inputs, padding=False, max_length=MAX_SEQUENCE_LENGTH, truncation=True, ) ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names) # Define a oneshot data collator for multimodal inputs. def data_collator(batch): assert len(batch) == 1 return {key: torch.tensor(value) for key, value in batch[0].items()} # Recipe recipe = [ GPTQModifier( targets="Linear", scheme="W8A8", sequential_targets=["Qwen2_5_VLDecoderLayer"], ignore=["lm_head", "re:visual.*"], ), ] SAVE_DIR==f"{model_id.split('/')[1]}-quantized.w8a8" # Perform oneshot oneshot( model=model, tokenizer=model_id, dataset=ds, recipe=recipe, max_seq_length=MAX_SEQUENCE_LENGTH, num_calibration_samples=NUM_CALIBRATION_SAMPLES, trust_remote_code_model=True, data_collator=data_collator, output_dir=SAVE_DIR ) ```
## Evaluation The model was evaluated using [mistral-evals](https://github.com/neuralmagic/mistral-evals) for vision-related tasks and using [lm_evaluation_harness](https://github.com/neuralmagic/lm-evaluation-harness) for select text-based benchmarks. The evaluations were conducted using the following commands:
Evaluation Commands ### Vision Tasks - vqav2 - docvqa - mathvista - mmmu - chartqa ``` vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7 python -m eval.run eval_vllm \ --model_name neuralmagic/pixtral-12b-quantized.w8a8 \ --url http://0.0.0.0:8000 \ --output_dir ~/tmp \ --eval_name ``` ### Text-based Tasks #### MMLU ``` lm_eval \ --model vllm \ --model_args pretrained="",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \ --tasks mmlu \ --num_fewshot 5 \ --batch_size auto \ --output_path output_dir ``` #### MGSM ``` lm_eval \ --model vllm \ --model_args pretrained="",dtype=auto,max_model_len=4096,max_gen_toks=2048,max_num_seqs=128,tensor_parallel_size=,gpu_memory_utilization=0.9 \ --tasks mgsm_cot_native \ --apply_chat_template \ --num_fewshot 0 \ --batch_size auto \ --output_path output_dir ```
### Accuracy
Category Metric Qwen/Qwen2.5-VL-3B-Instruct neuralmagic/Qwen2.5-VL-3B-Instruct-quantized.w4a16 Recovery (%)
Vision MMMU (val, CoT)
explicit_prompt_relaxed_correctness		 44.56 45.67 102.49%
VQAv2 (val)
vqa_match		 75.94 75.55 99.49%
DocVQA (val)
anls		 92.53 92.32 99.77%
ChartQA (test, CoT)
anywhere_in_answer_relaxed_correctness		 81.20 78.80 97.04%
Mathvista (testmini, CoT)
explicit_prompt_relaxed_correctness		 54.15 53.85 99.45%
Average Score 69.28 69.24 99.94%
Text MGSM (CoT) 43.69 41.98 96.09%
MMLU (5-shot) 65.32 64.83 99.25%
## Inference Performance This model achieves up to 1.33x speedup in single-stream deployment and up to 1.37x speedup in multi-stream asynchronous deployment, depending on hardware and use-case scenario. The following performance benchmarks were conducted with [vLLM](https://docs.vllm.ai/en/latest/) version 0.7.2, and [GuideLLM](https://github.com/neuralmagic/guidellm).
Benchmarking Command ``` guidellm --model neuralmagic/Qwen2.5-VL-3B-Instruct-quantized.w8a8 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=,generated_tokens=,images=,width=,height= --max seconds 120 --backend aiohttp_server ```
### Single-stream performance (measured with vLLM version 0.7.2)
Document Visual Question Answering
1680W x 2240H
64/128		 Visual Reasoning
640W x 480H
128/128		 Image Captioning
480W x 360H
0/128
Hardware Model Average Cost Reduction Latency (s) Queries Per Dollar Latency (s)th> Queries Per Dollar Latency (s) Queries Per Dollar
A6000x1 Qwen/Qwen2.5-VL-3B-Instruct 3.1 1454 1.8 2546 1.7 2610
neuralmagic/Qwen2.5-VL-3B-Instruct-quantized.w8a8 1.27 2.6 1708 1.3 3340 1.3 3459
neuralmagic/Qwen2.5-VL-3B-Instruct-quantized.w4a16 1.57 2.4 1886 1.0 4409 1.0 4409
A100x1 Qwen/Qwen2.5-VL-3B-Instruct 2.2 920 1.3 1603 1.2 1636
neuralmagic/Qwen2.5-VL-3B-Instruct-quantized.w8a8 1.09 2.1 975 1.2 1743 1.1 1814
neuralmagic/Qwen2.5-VL-3B-Instruct-quantized.w4a16 1.20 2.0 1011 1.0 2015 1.0 2012
H100x1 Qwen/Qwen2.5-VL-3B-Instruct 1.5 740 0.9 1221 0.9 1276
neuralmagic/Qwen2.5-VL-3B-Instruct-FP8-Dynamic 1.06 1.4 768 0.9 1276 0.8 1399
neuralmagic/Qwen2.5-VL-3B-Instruct-quantized.w4a16 1.24 0.9 1219 0.9 1270 0.8 1304
**Use case profiles: Image Size (WxH) / prompt tokens / generation tokens **QPD: Queries per dollar, based on on-demand cost at [Lambda Labs](https://lambdalabs.com/service/gpu-cloud) (observed on 2/18/2025). ### Multi-stream asynchronous performance (measured with vLLM version 0.7.2)
Document Visual Question Answering
1680W x 2240H
64/128		 Visual Reasoning
640W x 480H
128/128		 Image Captioning
480W x 360H
0/128
Hardware Model Average Cost Reduction Maximum throughput (QPS) Queries Per Dollar Maximum throughput (QPS) Queries Per Dollar Maximum throughput (QPS) Queries Per Dollar
A6000x1 Qwen/Qwen2.5-VL-3B-Instruct 0.5 2405 2.6 11889 2.9 12909
neuralmagic/Qwen2.5-VL-3B-Instruct-quantized.w8a8 1.26 0.6 2725 3.4 15162 3.9 17673
neuralmagic/Qwen2.5-VL-3B-Instruct-quantized.w4a16 1.39 0.6 2548 3.9 17437 4.7 21223
A100x1 Qwen/Qwen2.5-VL-3B-Instruct 0.8 1663 3.9 7899 4.4 8924
neuralmagic/Qwen2.5-VL-3B-Instruct-quantized.w8a8 1.06 0.9 1734 4.2 8488 4.7 9548
neuralmagic/Qwen2.5-VL-3B-Instruct-quantized.w4a16 1.10 0.9 1775 4.2 8540 5.1 10318
H100x1 Qwen/Qwen2.5-VL-3B-Instruct 1.1 1188 4.3 4656 4.3 4676
neuralmagic/Qwen2.5-VL-3B-Instruct-FP8-Dynamic 1.15 1.4 1570 4.3 4676 4.8 5220
neuralmagic/Qwen2.5-VL-3B-Instruct-quantized.w4a16 1.96 4.2 4598 4.1 4505 4.4 4838
**Use case profiles: Image Size (WxH) / prompt tokens / generation tokens **QPS: Queries per second. **QPD: Queries per dollar, based on on-demand cost at [Lambda Labs](https://lambdalabs.com/service/gpu-cloud) (observed on 2/18/2025).