Nemotron Labs Dory 1.0 4B
Nemotron Labs Dory 1.0 4B is a released rag, agents, and long context model with open-weight and 256K context; evaluate it while provider pricing coverage matures.
- Family
- Nemotron-Labs-Dory
- Released
- 2026-10-16
- Context
- 256K
- Parameters
- 4B
- Architecture
- Decoder Only
- Knowledge cutoff
- 2025-09
- Specialization
- general
- Openness
- Open weights
- License
- OpenMDW 1.1Permitted
- Weights
- Available
- Code
- Unknown
- Training
- Multi-stage
No tracked provider pricing is available yet.
About
Nemotron Labs Dory 1.0 4B is an open-weight NVIDIA research model with 4 billion parameters and a 256K-token context window. It uses a looped (latent-recurrent) normalized-GPT design with interleaved sliding-window and full attention, so it can re-run its recurrent layers 1 to 4 times per token to trade compute for accuracy. It was pre-trained on 6T tokens, partly in native NVFP4, then post-trained with SFT and GRPO reinforcement learning for reasoning and tool use. English only. Weights are available in BF16, MXFP8, NVFP4 and GGUF under OpenMDW-1.1.
Providers
No active provider routes are tracked for this model yet.
Capabilities
Benchmark peer barsfor RAG
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/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-MXFP8nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-NVFP4nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-GGUFNo tracked provider pricing is available yet.