Identity
- Status
- active
- Developer ID
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16- Released
- Aug 11, 2026
- Version
- NVIDIA Nemotron 3.5 Lightning 30B-A3B
- License
- openmdw-1.1
NVIDIANVIDIA Nemotron 3.5 Lightning 30B-A3B
NVIDIA Nemotron 3.5 Lightning 30B-A3B is an open-weight hybrid Mamba-2, mixture-of-experts, and attention model with 30B total parameters, 3B active parameters, and up to 1M tokens of context.
- Context
- 1,048,576 tokens
- Inputs
- Text
- Outputs
- Text
- Released
- Aug 11, 2026
Providers & Pricing
Estimate workload cost →Benchmarks
All benchmark results →| LMArena Text Arenatext-2026-09-01-011508720696 | 1,331.84 | — | 4,533 | nvidia-nemotron-3.5-lightning-30b-a3b-nvfp4; 95% CI [1322.39322537, 1341.28358716]; votes 4533; rank 207unknown | Original sourcewinner eligible | Third-party benchmark |
At a Glance
Model Facts
Capacity
- Context
- 1,048,576 tokens
- Maximum output
- Unknown
- Total parameters
- 30,000,000,000
- Active parameters
- 3,000,000,000
- Knowledge cutoff
- Not reported
Interface and Access
- Inputs
- Text
- Outputs
- Text
- API available
- Unknown
- Open weights
- Yes
- Self-hostable
- Yes
- Reasoning
- Yes
- Vision
- No
- Tool calling
- Yes
- Capabilities
- agents, chat, generation, reasoning, tools
This page represents one immutable developer model ID. Serving endpoints, pricing, regions, quantizations, and service tiers attach separately and never create duplicate model records.
Version Lineage
PredecessorUnknown
SuccessorsUnknown
Aliasesnemotron-3.5-lightning-30b-a3b, NVIDIA Nemotron 3.5 Lightning 30B A3B, nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
Explicit Unknowns
- Maximum output
- Knowledge cutoff
- API availability
Primary Evidence
Sources and Observation Date
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 developer model repositoryNVIDIA · observed Sep 3, 2026nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 README.md at a9904d24bcc1NVIDIA · observed Sep 3, 2026nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 immutable Hub API metadataNVIDIA · observed Sep 3, 2026nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 tokenizer_config.json at a9904d24bcc1NVIDIA · observed Sep 3, 2026Fireworks Ai catalogFireworks Ai · observed Sep 3, 2026
Comparable Peers
Related Model Comparisons
| A | Pair | B | Context |
|---|---|---|---|
| vs | family variantstext | ||
| vs | InklingThinking Machines Lab | cross-developer peerstext | |
| vs |  DeepSeek-V4-Pro-0813DeepSeek | cross-developer peerstext | |
| vs |  Qwen3.8-MaxQwen | cross-developer peerstext | |
| vs |  GLM-5.3Z.ai | cross-developer peerstext | |
| vs | cross-developer peerstext | ||
| vs |  Command A ReasoningCohere | cross-developer peerstext | |
| vs | family variantstext | ||
| vs | Seed 2.0 CodeByteDance Seed | cross-developer peerstext | |
| vs | family variantstext | ||
| vs | family variantstext | ||
| vs | DeepSeek-V4-ProDeepSeek | cross-developer peerstext |
Questions
NVIDIA Nemotron 3.5 Lightning 30B-A3B FAQs
What is NVIDIA Nemotron 3.5 Lightning 30B-A3B?+
NVIDIA Nemotron 3.5 Lightning 30B-A3B is an open-weight hybrid Mamba-2, mixture-of-experts, and attention model with 30B total parameters, 3B active parameters, and up to 1M tokens of context. It is developed by NVIDIA and its current sourced lifecycle status is active.
What inputs and outputs does NVIDIA Nemotron 3.5 Lightning 30B-A3B support?+
NVIDIA Nemotron 3.5 Lightning 30B-A3B's current record lists Text as input and Text as output.
How much context does NVIDIA Nemotron 3.5 Lightning 30B-A3B support?+
The current record lists a 1,048,576-token context window and does not report a maximum output length.
Is NVIDIA Nemotron 3.5 Lightning 30B-A3B available through an API?+
NVIDIA Nemotron 3.5 Lightning 30B-A3B's current primary-source record does not establish API availability. No provider endpoint is treated as available without direct provider evidence.
How large is NVIDIA Nemotron 3.5 Lightning 30B-A3B?+
The current record lists 30,000,000,000 total parameters and 3,000,000,000 active parameters. Its architecture is NemotronHForCausalLM.
What capabilities and tasks does NVIDIA Nemotron 3.5 Lightning 30B-A3B support?+
NVIDIA Nemotron 3.5 Lightning 30B-A3B's recorded capabilities are agents, chat, generation, reasoning, and tools. Its supported tasks are coding, reasoning, and text.
How much does NVIDIA Nemotron 3.5 Lightning 30B-A3B cost through an API?+
No directly sourced token price is currently attached to NVIDIA Nemotron 3.5 Lightning 30B-A3B. Missing prices remain unknown rather than being inferred from another model or provider.
Can NVIDIA Nemotron 3.5 Lightning 30B-A3B be self-hosted?+
NVIDIA Nemotron 3.5 Lightning 30B-A3B is an open-weight model. Self-hosting is supported, and the recorded license is openmdw-1.1.
Does NVIDIA Nemotron 3.5 Lightning 30B-A3B have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are nemotron-3.5-lightning-30b-a3b, NVIDIA Nemotron 3.5 Lightning 30B A3B, and nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16.
Which models can NVIDIA Nemotron 3.5 Lightning 30B-A3B be compared with?+
The current compatible peer set includes NVIDIA-Nemotron-3-Nano-30B-A3B-BF16, Inkling, DeepSeek-V4-Pro-0813, Qwen3.8-Max, and GLM-5.3. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →