NVIDIA model product
llama-nemotron-colembed-vl-3b-v2
Ranked model from MTEB.
Updated Aug 18, 2026. Default version: llama-nemotron-colembed-vl-3b-v2
LLMBoard Embedding Score52.0llama-nemotron-colembed-vl-3b-v2
Coverage5%1 benchmark families
Context window8.2KTokens
Official input priceN/AOfficial price unavailable
llama-nemotron-colembed-vl-3b-v2 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
llama-nemotron-colembed-vl-3b-v2 Benchmark Results
Benchmark scores for llama-nemotron-colembed-vl-3b-v2.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkMIEB(eng) Multimodal | Score91.7% | Rank08 | Participants83 | PercentileN/A | EvidenceA | Evaluated |
llama-nemotron-colembed-vl-3b-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.
llama-nemotron-colembed-vl-3b-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.
llama-nemotron-colembed-vl-3b-v2 Runtime Performance
Provider-specific output speed and catalog latency for llama-nemotron-colembed-vl-3b-v2. Runtime does not affect the capability score.
No runtime data
Browse runtime rankingsNo 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.
llama-nemotron-colembed-vl-3b-v2 Specifications
Technical details for the model's default version.
- Version
- llama-nemotron-colembed-vl-3b-v2
- Released
- Jan 21, 2026
- Knowledge cutoff
- Unknown
- Parameters
- 4.4B
- Context window
- 8.2K
- Max output
- N/A
- Inputs
- image, text
- Outputs
- embedding
- Open weights
- Yes
- License
- https://huggingface.co/nvidia/llama-nemotron-colembed-vl-3b-v2/blob/main/LICENSE
llama-nemotron-colembed-vl-3b-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 |
|---|
| Versionllama-nemotron-colembed-vl-3b-v2 | Released | LLMBoard52.0 | Parameters4.4B | Context8.2K | Max outputN/A | Open weightsYes | Licensehttps://huggingface.co/nvidia/llama-nemotron-colembed-vl-3b-v2/blob/main/LICENSE |
llama-nemotron-colembed-vl-3b-v2 vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
llama-nemotron-colembed-vl-3b-v2vsArgus-Colqwen3.5-4b-v0-bf16llama-nemotron-colembed-vl-3b-v2vsbge-base-enllama-nemotron-colembed-vl-3b-v2vsVultronRetrieverPrime-Qwen3.5-8Bllama-nemotron-colembed-vl-3b-v2vsnemotron-colembed-vl-4b-v2llama-nemotron-colembed-vl-3b-v2vscolqwen3.5-4.5B-v3llama-nemotron-colembed-vl-3b-v2vsLCO-Embedding-Omni-7B
Models similar to llama-nemotron-colembed-vl-3b-v2
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
NV
nemotron-colembed-vl-4b-v2
NVIDIA
NV
nemotron-colembed-vl-8b-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 llama-nemotron-colembed-vl-3b-v2?
Key information about llama-nemotron-colembed-vl-3b-v2 and its available data.
Ranked model from MTEB.
Data as of 2026-08-17.
FAQ
Common questions about llama-nemotron-colembed-vl-3b-v2.
When was llama-nemotron-colembed-vl-3b-v2 released?
llama-nemotron-colembed-vl-3b-v2's default version was released on Jan 21, 2026.
How much does llama-nemotron-colembed-vl-3b-v2 cost?
No official standard PAYG price is currently available for llama-nemotron-colembed-vl-3b-v2.
Who created llama-nemotron-colembed-vl-3b-v2?
llama-nemotron-colembed-vl-3b-v2 was created by NVIDIA.
What is the context window for llama-nemotron-colembed-vl-3b-v2?
The default version has a 8.2K token context window.
Is llama-nemotron-colembed-vl-3b-v2 open weight?
Yes. The default version is marked as open weight under https://huggingface.co/nvidia/llama-nemotron-colembed-vl-3b-v2/blob/main/LICENSE.
How many API providers offer llama-nemotron-colembed-vl-3b-v2?
No provider offering is currently linked to the default version.
What models should I compare llama-nemotron-colembed-vl-3b-v2 with?
Nearby ranked alternatives include Argus-Colqwen3.5-4b-v0-bf16, bge-base-en, VultronRetrieverPrime-Qwen3.5-8B.