[Models](/models)/MCG-NJU/OneStreamer-4B

Apache 2.0

# OneStreamer-4B

by MCG-NJU

A 4B streaming video model that keeps time-stamped memory and decides when to speak, 72.1 on OVOBench

9likes

4.4B (Qwen3-VL-4B base)params

[HuggingFace](https://huggingface.co/MCG-NJU/OneStreamer-4B)[Run it on your own data, free](https://studio.mixpeek.com/namespaces/create?mode=managed&utm_source=homepage&utm_medium=model_page&utm_campaign=mvs_onramp)

Identifiers

Model ID

`MCG-NJU/OneStreamer-4B`

## Deploy OneStreamer-4B

Single-tenant

Mixpeek has no managed extractor for this model. On a single-tenant deployment you upload the weights and a custom plugin serves them next to the rest of your pipeline.

[Read the customer-hosted guide](https://mixpeek.com/docs/customer-hosted/overview) [Talk to us about single-tenant](/demo)

## Overview

OneStreamer-4B is a streaming video-language model from Nanjing University's MCG lab, built on Qwen3-VL-4B-Instruct and released under Apache 2.0 in September 2026. It reads video as it arrives through a recent visual window, keeps a time-aligned caption memory of what it has seen, and decides on its own when it has enough evidence to answer.

While watching it emits a silence token to keep observing, a standby token when it needs more evidence, or a response token followed by an answer. The card reports gains over the Qwen3-VL-4B base on eight streaming-video benchmarks, including 72.1 against 58.8 on OVOBench and 48.7 against 34.3 on ProactiveVideoQA.

## Architecture

Qwen3-VL-4B-Instruct (about 4.4B parameters) trained for streaming interaction. Video is processed incrementally through a recent visual window, with PHCM retaining a time-aligned caption memory for later questions. Proactive responses are controlled by Silence, Standby and Response tokens. Training data is the OneStreamer-1M dataset.

## Mixpeek SDK Integration

IngestRetrieve

\# OneStreamer runs on your side with the Inference/ code in its GitHub repository.
# Store each time-stamped caption it writes as a text object, so a Mixpeek text
# collection can search the stream later.
import requests

for cap in captions:  # e.g. {"start": 1312.0, "end": 1318.5, "text": "A forklift enters aisle 4"}
    requests.post(
        "https://api.mixpeek.com/v1/buckets/bkt\_your\_bucket/objects",
        headers={"Authorization": "Bearer API\_KEY", "X-Namespace": "ns\_your\_namespace"},
        json={"blobs": \[{"property": "caption", "type": "text", "data": cap\["text"\]}\],
              "metadata": {"stream": "dock-cam-2", "start": cap\["start"\], "end": cap\["end"\]}},
    )

## Capabilities

*   Streaming video input through a recent visual window
*   Time-aligned caption memory for questions about earlier moments
*   Proactive replies: decides when it has seen enough to answer
*   English and Chinese
*   Apache 2.0 license

## Use Cases on Mixpeek

Live camera or broadcast monitoring that answers when an event happens

Assistants that answer questions about something shown minutes earlier

Producing time-stamped captions of a stream for later search

## Benchmarks

Dataset

Metric

Score

Source

OVOBench

Overall

72.1

Model card: MCG-NJU/OneStreamer-4B (self-reported; Qwen3-VL-4B base 58.8)

StreamingBench

Real-Time

86.9

Model card (self-reported; base 81.8)

ODVBench

Overall

71.3

Model card (self-reported; base 57.6)

ProactiveVideoQA

Average

48.7

Model card (self-reported; base 34.3)

OVO-Timing

Average F1

41.6

Model card (self-reported; base 29.4)

## Performance

Input SizeStreaming video frames through a recent window, with text questions in English or Chinese

Embedding Dimn/a (outputs text)

GPU LatencyInput dependent

GPU ThroughputBatch dependent

GPU MemoryModel dependent

Scores are the card's, each benchmark on its own metric. The OmniMMI result uses speech recognition for some subtasks. We have not measured it.

## Common Pipeline Companions

[

Qwen/Qwen3-VL-4B-Instruct

The base model, for offline questions about a whole clip

](/model/Qwen/Qwen3-VL-4B-Instruct)[

netease-youdao/Confucius4-R2T2

Streaming speech recognition for what is said in the stream

](/model/netease-youdao/Confucius4-R2T2)

## Frequently Asked Questions

### What is OneStreamer-4B?

A streaming video-language model built on Qwen3-VL-4B-Instruct. It watches video as it arrives, keeps a time-aligned memory of what it saw, and decides when to answer.

### How is a streaming video model different from a normal video model?

A normal video model reads a finished clip and then answers. A streaming model reads frames as they arrive, has to remember earlier moments without re-reading them, and here also chooses when to speak, which matters for live feeds.

### How well does OneStreamer-4B score?

The card reports 72.1 on OVOBench, 86.9 on StreamingBench real-time and 48.7 on ProactiveVideoQA, each well above the Qwen3-VL-4B base model.

### How do I search what OneStreamer saw with Mixpeek?

Store each time-stamped caption it writes as a text object with the stream name and times in metadata, then search them with a text retriever, as in the example on this page.

## Explore on Mixpeek

[

Browse all models

Search the full model catalog

](/models)[

Feature Extractors

See how Mixpeek runs models as extractors

](/extractors)[

Mixpeek Vector Store

Store & search embeddings at scale

](/mvs)[

Pricing

Usage-based pricing for pipelines

](/pricing)[

All Curated Lists

Compare models, APIs & infrastructure

](/curated-lists)

### Specification

OrganizationMCG-NJU

Retriever\-

Parameters4.4B (Qwen3-VL-4B base)

LicenseApache 2.0

Downloads/moN/A

Likes9

[

### Research Paper

OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction

arxiv.org](https://arxiv.org/abs/2610.01762)

### Build a pipeline with OneStreamer-4B

Add this model to a processing pipeline alongside other extractors. Combine with retrieval stages for end-to-end search.

[Run it on your own data, free](https://studio.mixpeek.com/namespaces/create?mode=managed&utm_source=homepage&utm_medium=model_page&utm_campaign=mvs_onramp)