NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
Support summary
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 is a checkpoint published by NVIDIA, built on the NemotronHForCausalLM architecture. Official recipes or cookbooks cover vLLM and SGLang, without pinning a stable release. TensorRT-LLM lists its architecture, but not this exact checkpoint.
- Documented hardware
- NVIDIA / CUDA
- Documented quantization
- BF16
- Documented features
- Prefix caching, Reasoning parsers, Speculative decoding, and Tool calling
- Configured context
- 262,144 tokens
- License
- openmdw-1.1
Hardware, quantization and features count only statements about this checkpoint; engine-wide capabilities are listed with each release.
Hugging Face model card
- Publisher
- NVIDIA
- Task
- text generation
- License
- openmdw-1.1
- Library
- transformers
- Architecture
- NemotronHForCausalLM
- Weight tensor elements
- 31.6B
- Tensor types
- F32, BF16
- Configured context
- 262,144 tokens
- Languages
- en, es, fr, de, it, ja
- Weight access
- Public
- Repository created
- 2026-08-01
Publisher deployment guidance
- vLLM0.27.1 container
Publisher container vllm/vllm-openai:v0.27.1. The BF16 example fits a 262,144-token context on one H100 80GB; the 1M-token recipes use additional capacity and explicit context settings.
Source: nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 · publisher model cardReviewed - SGLangdev-nemotron3-5-lightning
Publisher development container, with separate H100 and B200 recipes and memory-dependent context settings.
Source: nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 · publisher model cardReviewed
Model notes and sources
- nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 · publisher model card
- nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 · Hugging Face metadata
- nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 · publisher configuration
- vllm · models/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16.yaml
- sglang · docs/src/snippets/configs/nvidia/nemotron-3.5-lightning.jsx
- sglang · docs/cookbook/autoregressive/NVIDIA/Nemotron3.5-Lightning.mdx
- Reviewed
Engine support
3 engines
| Engine | Release | Checkpoint support | Evidence scope | Last known supported |
|---|---|---|---|---|
| vLLM | 0.28.0Recipe / cookbook | Documented recipeSource: vllm · models/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16.yamlReviewed | No supported release indexed | |
Features, dependencies and evidence for vLLM 0.28.0 | ||||
| SGLang | Version not pinnedRecipe / cookbook | Documented recipeSource 1: sglang · docs/cookbook/autoregressive/NVIDIA/Nemotron3.5-Lightning.mdxSource 2: sglang · docs/src/snippets/_deployment.jsxSource 3: sglang · docs/src/snippets/configs/nvidia/nemotron-3.5-lightning.jsxSource 4: sglang · docs/src/snippets/configs/nvidia/nemotron-3.5-lightning-benchmarks.jsxSource 5: sglang · docs/src/snippets/_playground.jsxReviewed | No supported release indexed | |
Features, dependencies and evidence for SGLang 0.5.19 | ||||
| TensorRT-LLM | 1.2.1Newest indexed | Architecture listed; exact checkpoint unknown | No supported release indexed | |
Features, dependencies and evidence for TensorRT-LLM 1.2.1 | ||||