nemotron-colembed-vl-8b-v2
Embeddingtransformerssafetensorsqwen3_vl_nemotron_embedfeature-extractiontextimagevidorecolpalimultimodal-embeddingmultilingual-embeddingText-to-Visual Document (T→VD) retrievalvisual-document-retrievalcustom_codemultilingualarxiv:2602.03992arxiv:2511.21631license:cc-by-nc-4.0region:us
Context
Unknown / Not disclosed
Max Output
Unknown / Not disclosed
Released
1/15/2026
Providers
1
Overview
nemotron-colembed-vl-8b-v2 is a large language model developed by NVIDIA. It supports unknown context context and is available through 1 API provider(s).
Key Highlights
- Embedding
Brand
NVIDIA
Organization
Country: USA
View all models, pricing and details from NVIDIA.
Specifications
Basic Information
| Model | nemotron-colembed-vl-8b-v2 |
| Brand | NVIDIA |
| Version | 2 |
| Model Type | transformers |
| Status | stable |
| Released | 1/15/2026 |
| Popularity | 8873 |
Architecture
| Parameter Size | 8.8B |
| Architecture Type | qwen3_vl_nemotron_embed |
| Attention Mechanism | Unknown / Not disclosed |
| Tokenizer | Unknown / Not disclosed |
| Vocabulary Size | Unknown / Not disclosed |
Context & I/O
| Context | Unknown / Not disclosed |
| Max Output | Unknown / Not disclosed |
| Modalities | Embedding |
| Languages | multilingual |
Capabilities
| Vision | No |
| Audio | No |
| Reasoning | No |
| Function Call | No |
| MCP | No |
| JSON Mode | No |
| Embedding | Yes |
Training Data
| Training Dataset | Unknown / Not disclosed |
| Estimated Data Size | Unknown / Not disclosed |
| Knowledge Cutoff | Unknown / Not disclosed |
Inference & Deployment
| API Access | Yes |
| VRAM Estimate | Unknown / Not disclosed |
| Quantization Support | Unknown / Not disclosed |
| Hardware Requirements | Unknown / Not disclosed |
Safety & Compliance
| Safety Evaluations | Unknown / Not disclosed |
| Content Policy | Unknown / Not disclosed |
| Region Restrictions | Unknown / Not disclosed |
License & Pricing
| License | cc-by-nc-4.0 |
| Commercial Use | Unknown / Not disclosed |
| Open Source | Yes |
Provider & Pricing
| Provider | Input | Output | Cache | Batch | Website |
|---|---|---|---|---|---|
| nvidia | $0.000/1M | $0.000/1M | - | - | Visit Website |
Price Changes
No recorded price changes.
Benchmarks
No benchmark data available.
Changelog
- Page created / data imported9/23/2026
- Last updated9/23/2026
Frequently Asked Questions
What is nemotron-colembed-vl-8b-v2?
nemotron-colembed-vl-8b-v2 is a large language model developed by NVIDIA.
Who developed nemotron-colembed-vl-8b-v2?
nemotron-colembed-vl-8b-v2 was developed by NVIDIA. You can learn more on the brand page or official website.
What is the context length of nemotron-colembed-vl-8b-v2?
The context length of nemotron-colembed-vl-8b-v2 has not been publicly disclosed.
How much does nemotron-colembed-vl-8b-v2 API cost?
API pricing for nemotron-colembed-vl-8b-v2 starts at $0.000/1M per 1M input tokens and $0.000/1M per 1M output tokens. See the pricing table above for provider-specific rates.