Nemotron 3.5 Bolt 74B-A9B
Nemotron 3.5 Bolt 74B-A9B is available now for rag, agents, and long context with open-weight and 256K context; evaluate it while provider pricing coverage matures.
- Family
- Nemotron 3.5
- Released
- 2026-10-15
- Context
- 256K
- Parameters
- 74B (9B activated)
- Architecture
- MoE + SSM Hybrid
- Specialization
- general
- Openness
- Open weights
- License
- OpenMDW 1.1Commercial use: permitted
- Weights
- Available
- Code
- Unknown
- Training
- Multi-stage
No tracked provider pricing is available yet.
About
Nemotron 3.5 Bolt 74B-A9B is an open-weight vision-language model from NVIDIA, a 74-billion-parameter hybrid Mamba-Transformer mixture-of-experts with about 9 billion active parameters and a 256K-token context window. It was compressed from Nemotron 3.5 Super VL, and its 24GB version uses native 2-bit quantization to run local agentic workloads on NVIDIA RTX and DGX Spark systems.
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-3.5-Bolt-74B-A9B-BF16nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GBnvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-GGUFnvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-LiLiCorrnvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-LiLiCorr-GGUFNo tracked provider pricing is available yet.