NVIDIA model product
nemotron-colembed-vl-8b-v2
nemotron-colembed-vl-8b-v2 is an embedding model from NVIDIA ranked by MTEB.
Updated Sep 8, 2026. Default version: nemotron-colembed-vl-8b-v2
LLMBoard Embedding Score62.9nemotron-colembed-vl-8b-v2
Coverage35%2 benchmark families
Context window262.1KTokens
Official input priceN/AOfficial price unavailable
nemotron-colembed-vl-8b-v2 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
nemotron-colembed-vl-8b-v2 Benchmark Results
Benchmark scores for nemotron-colembed-vl-8b-v2.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkMIEB English Multimodal | Score92.65% | Rank02 | Participants84 | Percentile98.80% | EvidenceA | EvaluatedN/A |
| BenchmarkViDoRe v3 Overall | Score63.42% | Rank05 | Participants40 | Percentile89.74% | EvidenceA | EvaluatedN/A |
nemotron-colembed-vl-8b-v2 Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
nemotron-colembed-vl-8b-v2 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- N/A
- Tracked offerings
- 0
No provider prices
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
nemotron-colembed-vl-8b-v2 Runtime Performance
Provider-specific output speed and catalog latency for nemotron-colembed-vl-8b-v2. Runtime does not affect the capability score.
No runtime data
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
nemotron-colembed-vl-8b-v2 Specifications
Technical details for the model's default version.
- Version
- nemotron-colembed-vl-8b-v2
- Released
- Jan 7, 2026
- Knowledge cutoff
- Unknown
- Parameters
- 8.7B
- Context window
- 262.1K
- Max output
- N/A
- Inputs
- image, text
- Outputs
- embedding
- Open weights
- Yes
- License
- https://huggingface.co/nvidia/nemotron-colembed-vl-8b-v2/blob/main/LICENSE
nemotron-colembed-vl-8b-v2 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| Versionnemotron-colembed-vl-8b-v2 | Released | LLMBoard62.90 | Parameters8.7B | Context262.1K | Max outputN/A | Open weightsYes | Licensehttps://huggingface.co/nvidia/nemotron-colembed-vl-8b-v2/blob/main/LICENSE |
Models similar to nemotron-colembed-vl-8b-v2
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
NV
nemotron-colembed-vl-4b-v2
NVIDIA
NV
llama-nemotron-colembed-vl-3b-v2
NVIDIA
NV
llama-nemoretriever-colembed-3b-v1
NVIDIA
NV
llama-nemoretriever-colembed-1b-v1
NVIDIA
NV
NV-Embed-v1
NVIDIA
NV
NV-Embed-v2
NVIDIA
What is nemotron-colembed-vl-8b-v2?
Key information about nemotron-colembed-vl-8b-v2 and its available data.
nemotron-colembed-vl-8b-v2 is an embedding model from NVIDIA. It is ranked by MTEB.
Data as of 2026-09-08.
FAQ
Common questions about nemotron-colembed-vl-8b-v2.
When was nemotron-colembed-vl-8b-v2 released?
nemotron-colembed-vl-8b-v2's default version was released on Jan 7, 2026.
How much does nemotron-colembed-vl-8b-v2 cost?
No official standard PAYG price is currently available for nemotron-colembed-vl-8b-v2.
Who created nemotron-colembed-vl-8b-v2?
nemotron-colembed-vl-8b-v2 was created by NVIDIA.
What is the context window for nemotron-colembed-vl-8b-v2?
The default version has a 262.1K token context window.
Is nemotron-colembed-vl-8b-v2 open weight?
Yes. The default version is marked as open weight under https://huggingface.co/nvidia/nemotron-colembed-vl-8b-v2/blob/main/LICENSE.