# Dots3 Note Prev URL: https://interfaze.ai/models/dots-studiodots3-note-prev [All models](https://interfaze.ai/models) Dots3 Note Prev by dots-studio, a image-text-to-text model with multimodal capabilities. Understand and compare multimodal features, benchmarks, and capabilities. ## Comparison | Feature | Dots3 Note Prev | Interfaze | | --- | --- | --- | | Input Modalities | text, image, audio, video, document | image, text, audio, video, document | | Native OCR | No | Yes | | Long Document Processing | No | Yes | | Language Support | 100 partial | 162+ | | Native Speech-to-Text | No | Yes | | Native Object Detection | No | Yes | | Guardrail Controls | No | Yes | | Context Input Size | 524.3K | 1M | | Tool Calling | Yes | Tool calling supported + built in browser, code execution and web search | ### Scaling | Feature | Dots3 Note Prev | Interfaze | | --- | --- | --- | | Scaling | Self-hosted/Provider-hosted with quantization | Unlimited | [Try Interfaze](https://interfaze.ai/dashboard)[Read the Docs](https://interfaze.ai/docs) View model card on [Hugging Face](https://huggingface.co/dots-studio/dots3-note-prev) * * * ## Table of Contents - [Model Introduction](https://interfaze.ai/models/dots-studiodots3-note-prev#model-introduction) - [Model Overview](https://interfaze.ai/models/dots-studiodots3-note-prev#model-overview) - [Evaluation Results](https://interfaze.ai/models/dots-studiodots3-note-prev#evaluation-results) - [General Reasoning and Agent](https://interfaze.ai/models/dots-studiodots3-note-prev#general-reasoning-and-agent) - [Multimodal Understanding](https://interfaze.ai/models/dots-studiodots3-note-prev#multimodal-understanding) - [Model Links](https://interfaze.ai/models/dots-studiodots3-note-prev#model-links) - [Quickstart](https://interfaze.ai/models/dots-studiodots3-note-prev#quickstart) - [Deployment](https://interfaze.ai/models/dots-studiodots3-note-prev#deployment) - [Transformers](https://interfaze.ai/models/dots-studiodots3-note-prev#transformers) - [SGLang](https://interfaze.ai/models/dots-studiodots3-note-prev#sglang) - [vLLM](https://interfaze.ai/models/dots-studiodots3-note-prev#vllm) - [Benchmark Appendix](https://interfaze.ai/models/dots-studiodots3-note-prev#benchmark-appendix) - [License](https://interfaze.ai/models/dots-studiodots3-note-prev#license) - [Contact Us](https://interfaze.ai/models/dots-studiodots3-note-prev#contact-us) * * * ## Model Introduction dots3-note preview is the first open-weight model in the dots3 family. It is a Mixture-of-Experts model with 280B total parameters, 16B activated parameters, and support for a context length of up to 512K tokens. The model can understand text, images, video, and audio, and produces text outputs. dots3-note preview is optimized for a broad range of tasks, including: - General knowledge and instruction following; - Mathematical and logical reasoning; - Tool use and multi-step agent workflows; - Interactive tasks that require exploration, memory updates, and adaptation; - Code generation and code-based problem solving; - Image, document, chart, audio, and video understanding; - Long-context information processing. The dots3 family is designed to include models with different trade-offs among capability, latency, and inference cost. dots3-note preview is the most lightweight member of the family. ## Model Overview | Property | Value | | --- | --- | | Architecture | Multimodal MoE | | Total Parameters | 280B | | Activated Parameters | 16B | | MTP | 1 shared layer, 1.13B | | Number of Layers | 1 dense + 45 MoE | | Hidden Size | 5120 | | FFN Hidden Size | 13824 (dense), 1536 (per expert) | | Experts | 256 routed + 1 shared, top-8 | | Attention | 13 DSA + 33 SWA (~1:3) | | DSA | Top-2048 | | Context Length | 512K | | Vocabulary Size | 152K | | Vision Encoder | MoE ViT, 7B total, 1.2B activated | | Audio Encoder | Dense, 800M | | Supported Precision | BF16, FP8 | | Input | Text, image, video, audio | | Output | Text | ## Evaluation Results ### General Reasoning and Agent ![General Reasoning and Agent evaluation results](https://huggingface.co/dots-studio/dots3-note-prev/resolve/main/assets/bench_en1.png) ### Multimodal Understanding ![Multimodal Understanding evaluation results](https://huggingface.co/dots-studio/dots3-note-prev/resolve/main/assets/bench_en2.png) ## Model Links | Model Name | Description | HuggingFace | ModelScope | | --- | --- | --- | --- | | dots3-note-prev | Preview multimodal model | 🤗 Model | Model | | dots3-note-prev-fp8 | FP8-quantized preview multimodal model | 🤗 Model | Model | ## Quickstart Recommended: serve the FP8 checkpoint on one 8-GPU node with [SGLang](https://interfaze.ai/models/dots-studiodots3-note-prev#sglang) or [vLLM](https://interfaze.ai/models/dots-studiodots3-note-prev#vllm). ``` from openai import OpenAI client = OpenAI(base_url="http://127.0.0.1:8000/v1", api_key="EMPTY") response = client.chat.completions.create( model="dots3-note-prev", messages=[ {"role": "user", "content": "Hello! Can you briefly introduce yourself?"}, ], temperature=1.0, top_p=0.95, max_tokens=256, # Set enable_thinking=True for reasoning; False returns a direct response. extra_body={"chat_template_kwargs": {"enable_thinking": False}}, ) print(response.choices[0].message.content) ``` For a multimodal request, replace `messages` with one of these public examples: ``` examples = { "image": [ {"type": "image_url", "image_url": {"url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/cats.png"}}, {"type": "text", "text": "How many cats are in this image?"}, ], "audio": [ {"type": "audio_url", "audio_url": {"url": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/mary_had_lamb.mp3"}}, {"type": "text", "text": "Transcribe this nursery rhyme."}, ], "video": [ {"type": "video_url", "video_url": {"url": "https://huggingface.co/datasets/merve/vlm_test_images/resolve/main/concert.mp4"}}, {"type": "text", "text": "Describe the performance and what can be heard."}, ], } messages = [{"role": "user", "content": examples["image"]}] ``` Video inputs include their audio track when available. ## Deployment The commands below target FP8 on one 8-GPU node. BF16 requires more memory. Tune the context length to available memory, concurrency, and input modalities. Native support is available on [vLLM](https://recipes.vllm.ai/dots-studio/dots3-note-prev) `main`. [Transformers #47844](https://github.com/huggingface/transformers/pull/47844) and [SGLang #33829](https://github.com/sgl-project/sglang/pull/33829) are still under review; until they are merged, use the PR revisions below. ### Transformers First install mutually compatible [PyTorch and torchvision](https://pytorch.org/get-started/locally/) builds supported by your NVIDIA driver. For audio and video, also install a PyTorch-compatible `torchcodec` (included below) and FFmpeg with your system package manager. Then install [Transformers #47844](https://github.com/huggingface/transformers/pull/47844): ``` pip install accelerate pillow torchcodec kernels==0.16.0 "transformers @ git+https://github.com/huggingface/transformers.git@refs/pull/47844/head" ``` Run a minimal local inference: ``` from transformers import AutoModelForMultimodalLM, AutoProcessor model_id = "dots-studio/dots3-note-prev-fp8" processor = AutoProcessor.from_pretrained(model_id) model = AutoModelForMultimodalLM.from_pretrained(model_id, dtype="auto", device_map="auto") messages = [ {"role": "user", "content": "Hello! Please briefly introduce yourself."}, ] inputs = processor.tokenizer.apply_chat_template( messages, add_generation_prompt=True, return_tensors="pt", return_dict=True, enable_thinking=False, ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=128) print(processor.decode(outputs[0, inputs.input_ids.shape[1] :], skip_special_tokens=True)) ``` Use SGLang or vLLM for multi-GPU OpenAI-compatible serving. ### SGLang Recommended: use the release image [lmsysorg/sglang:dev-dots3-note](https://hub.docker.com/r/lmsysorg/sglang/tags). Full one-node recipes and tuning notes are in the [Dots3-Note cookbook](https://github.com/sgl-project/sglang/blob/main/docs/cookbook/autoregressive/RedNote/Dots3-Note.mdx). Source support is tracked in [SGLang #33829](https://github.com/sgl-project/sglang/pull/33829). Docker (the image downloads the checkpoint from Hugging Face on first run): ``` docker run --gpus all --ipc=host -p 8000:8000 \ lmsysorg/sglang:dev-dots3-note \ sglang serve \ --model-path dots-studio/dots3-note-prev-fp8 \ --served-model-name dots3-note-prev \ --host 0.0.0.0 \ --port 8000 \ --context-length 524288 \ --enable-dp-attention \ --dp-size 8 \ --tp-size 8 \ --ep-size 8 \ --moe-dense-tp-size 1 \ --page-size 64 \ --trust-remote-code \ --attention-backend fa3 \ --moe-a2a-backend deepep \ --enable-multimodal \ --speculative-algorithm NEXTN \ --speculative-num-steps 3 \ --speculative-eagle-topk 1 \ --speculative-num-draft-tokens 4 \ --speculative-draft-model-path dots-studio/dots3-note-prev-fp8 ``` Or install from source / the PR and run the same `sglang serve` arguments locally. `--attention-backend fa3` sets prefill, decode, and (when speculative decoding is enabled) draft attention. MTP/NEXTN (`--speculative-algorithm NEXTN` and the related flags) is optional and can reduce TPOT by more than 50%. Prefill CUDA graph is not supported yet. Optional features: ``` --language-only --tool-call-parser dots ``` ### vLLM Native dots3-note preview support is available on [vLLM](https://recipes.vllm.ai/dots-studio/dots3-note-prev) `main`. Use a recent nightly build until it is included in a stable release. The following example deploys the FP8 checkpoint on eight NVIDIA H100 GPUs with TP=8 and EP=8: ``` vllm serve dots-studio/dots3-note-prev-fp8 \ --served-model-name dots3-note-prev \ --host 0.0.0.0 \ --tensor-parallel-size 8 \ --enable-expert-parallel \ --moe-backend deep_gemm \ --max-model-len 262144 ``` Optional features: ``` --language-model-only --speculative-config '{"method":"mtp","num_speculative_tokens":3}' --enable-auto-tool-choice --tool-call-parser dots ``` ## Benchmark Appendix ![General Reasoning and Agent benchmark appendix](https://huggingface.co/dots-studio/dots3-note-prev/resolve/main/assets/benchmark_appendix_en_reasoning.png) ![Multimodal benchmark appendix](https://huggingface.co/dots-studio/dots3-note-prev/resolve/main/assets/benchmark_appendix_en_multimodal.png) ## License Copyright (c) 2026 Xiaohongshu. Developed and released by dots studio. The dots3-note preview model weights and modeling code in this repository are licensed under the Apache License, Version 2.0. See the LICENSE file for details. Transformers, SGLang, vLLM, and other third-party software are subject to their respective licenses. ## Contact Us For questions and feedback, please contact us through: - Email: [dots-model-feedback@xiaohongshu.com](mailto:dots-model-feedback@xiaohongshu.com) * * * dots3-note preview is developed and released by dots studio. ## Want more deterministic results? [Try Interfaze](https://interfaze.ai/dashboard)[Read the Docs](https://interfaze.ai/docs)