Data as of October 19, 2026 · How the score is built
Released Jul 20, 2026256K context
Cosmos3-Edge
Decision readingCosmos3-Edge is tracked, but not publicly ranked yet. The profile exposes 0 sourced benchmark rows and leaves unsupported fields blank until a published record exists.
Released Jul 20, 2026 — see all recent releases
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
edge · 4B
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- Not published
- Context window
- 256K
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not sourced yet
- Availability
- Open weights are available on Hugging Face under OpenMDW-1.1 for commercial and non-commercial use. NVIDIA provides PyTorch and vLLM-Omni integration guidance but no first-party hosted token price for this checkpoint.
- Cloud regions
- Not tracked yet
- Lifecycle
- Current
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing record
- Self-host
- Open weights available; hardware estimate not sourced
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track Cosmos3-Edge, but no weighted text-model benchmark result is published on the site yet. This page shows the metadata and separate protocol evidence we can verify now; a BenchLM score will appear only if compatible public evaluations land.
Cosmos3-Edge is a open weight model with a 256K context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Open weights are available on Hugging Face under OpenMDW-1.1 for commercial and non-commercial use. NVIDIA provides PyTorch and vLLM-Omni integration guidance but no first-party hosted token price for this checkpoint.
Official model-card snapshot for NVIDIA's July 20, 2026 Cosmos3-Edge release. The 4B Mixture-of-Transformers model combines an autoregressive reasoner with a diffusion generator for text, image, video, and action workflows. NVIDIA publishes physical-AI reasoning and generation charts, but no exact result maps to the current weighted LLM schema, so the model remains unranked.
The profile has no source-displayable benchmark row yet.
Last updated October 19, 2026. Runtime fields remain blank until a sourced snapshot exists.
Deployment options
Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.
Published weights are available, but BenchLM does not yet have a sourced parameter and VRAM profile for this exact model. Hardware cost estimates stay unavailable until that sizing record is complete.
Estimate VRAM from known parametersQuestions
How does Cosmos3-Edge perform overall in AI benchmarks?
Cosmos3-Edge does not have any source-displayable benchmark rows yet, so this profile does not assign a public score or rank. Documented specifications remain visible, while score-led charts and claims stay unavailable until a published evaluation can be attached to the exact model.
Is Cosmos3-Edge open source?
Cosmos3-Edge is an open-weight model from NVIDIA. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.
Does Cosmos3-Edge have full benchmark coverage on BenchLM?
No. Cosmos3-Edge currently has 0 source-displayable rows across 686 tracked benchmark slots. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Cosmos3-Edge?
Cosmos3-Edge has a reported context window of 256K in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.