Nemotron 3.5 Rerank 8B
Nemotron 3.5 Rerank 8B is a released general LLM work model with open-weight; evaluate it while provider pricing coverage matures.
- Family
- NV-Embed
- Released
- 2026-10-20
- Context
- 32K
- Parameters
- 8.38B
- Architecture
- Encoder Only
- Specialization
- ranking
- Openness
- Open weights
- License
- OpenMDW 1.1Permitted
- Weights
- Available
- Code
- Unknown
- Training
- Fine-tuned
No tracked provider pricing is available yet.
About
Nemotron 3.5 Rerank 8B is an open-weight NVIDIA multimodal, multilingual reranker with 8.38 billion parameters and a 32,768-token context. It scores how relevant a document (text, page image, or both, including charts and tables) is to a text query, to reorder candidates from an embedding retriever in vision RAG pipelines. It uses a Pixtral-based vision encoder and a bidirectional Ministral 3 language tower derived from Ministral 3 8B. Weights are under OpenMDW-1.1 for commercial use.
Providers
No active provider routes are tracked for this model yet.
Capabilities
Benchmark peer barsfor Coding
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
API versions
nvidia/Nemotron-3.5-Rerank-8B-BF16No tracked provider pricing is available yet.