Not runnable todayEmbeddingVerified 2026-11-05
InternVideo2 Stage2 6B
OpenGVLab/InternVideo2-Stage2_6B
InternVideo2 Stage2 6B is a video and text embedding model (MIT). Not runnable on Mixpeek today.
Something blocks it today, such as the license, remote code or a GPU-only runtime. The reason is below.
No demo for InternVideo2 Stage2 6B yet
A video, image, slideshow or playground goes here once we record one on our own data.
What it is good and bad at
- Best at
- State-of-the-art video-text retrieval and action recognition among open video encoders (per the paper).
- Worst at
- 6.4B parameters: multi-GPU-class memory; far too large for scale-to-zero CPU.
- Task
- Embedding
- Input
- Video, Text
- Output
- Vector
- Use cases
- Video understanding, Action recognition
Templates that use it
No template uses this model yet. Browse templates.
Input and output
Input
- video
- frames
- 4 to 8 per clip
- resolution
- 224x224
- text
Output
- vector
- dims
- not verified here
- distance
- cosine
- type
- dense
How Mixpeek wires it
- Extractors
- None today
- Feature URIs
- None today
- Vector indexes
- None
- Retriever stages
- None
- Combines with
- scene splits (transcoding/multimodal extractor) -> clip-level vectors -> feature_search with a text query
How it runs
- Status
- Not runnable today Requires trust_remote_code (custom_code on the hub) and a large GPU. Would run as a GPU batch plugin only after vendoring the model code.
- Serve apps
- None
- Runtime
- transformers AutoModel with trust_remote_code=True
- Weights
- safetensors, needs remote code
- Parameters
- 6,367 M
- Size on disk
- 25,000 MB
- Preprocessing
- Sample frames, resize to 224, normalize.
- Postprocessing
- L2-normalize projections.
- Serving
- batch
- Hardware
- Needs a GPU
Scale to zero
- Minimum replicas
- 0
- Maximum replicas
- 1
- Idle timeout
- 600 s
- Memory
- 40 GB
- CPUs
- 8
- GPUs
- 1
- Cold start, node warm
- Not recorded
- Cold start, new node
- Not recorded
Measured cost
Unmeasured
No committed measurement; plan row 3 measures it in the standalone image.
Our evaluations
Unmeasured
We have not evaluated this model on our own data yet. Publisher results are in the sources below.
Questions
- What is InternVideo2 Stage2 6B best at?
- State-of-the-art video-text retrieval and action recognition among open video encoders (per the paper).
- What are the limits of InternVideo2 Stage2 6B?
- 6.4B parameters: multi-GPU-class memory; far too large for scale-to-zero CPU.
- Can InternVideo2 Stage2 6B be used commercially?
- Yes. MIT per the hub tag.
- How does InternVideo2 Stage2 6B run on Mixpeek?
- Requires trust_remote_code (custom_code on the hub) and a large GPU. Would run as a GPU batch plugin only after vendoring the model code.