NVIDIA-Nemotron-3-Nano-30B-A3B-FP8
Support summary
NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 is a checkpoint published by NVIDIA, built on the NemotronHForCausalLM architecture. TensorRT-LLM 1.2.1, the newest indexed TensorRT-LLM release, documents support. Official recipes or cookbooks cover vLLM and SGLang, without pinning a stable release.
TensorRT-LLM documents support in 2 of 2 indexed releases, from 1.2.0 to 1.2.1.
- Documented quantization
- FP8
- Documented features
- Reasoning parsers and Tool calling
- Configured context
- 262,144 tokens
- License
- nvidia-nemotron-open-model-license
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
- Library
- transformers
- Architecture
- NemotronHForCausalLM
- Weight tensor elements
- 31.6B
- Tensor types
- F32, BF16, F8_E4M3
- Configured context
- 262,144 tokens
- Languages
- en, es, fr, de, ja, it
- Base models
- nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
- Weight access
- Public
- Repository created
- 2025-12-06
Model notes and sources
Explicit FP8 checkpoint in TensorRT-LLM’s support list; other variants need separate records.
- TensorRT-LLM v1.2.1 · docs/source/models/supported-models.md · 2 indexed revisions, v1.2.0 to v1.2.1
- nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 publisher metadata
- nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 · publisher model card
- nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 · Hugging Face metadata
- nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 · publisher configuration
- vllm · models/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16.yaml
- sglang · docs/cookbook/autoregressive/NVIDIA/Nemotron3-Nano.mdx
- vllm · NVIDIA/Nemotron-3-Nano-30B-A3B.md
- Reviewed
Engine support
3 engines
| Engine | Release | Checkpoint support | Evidence scope | Last known supported |
|---|---|---|---|---|
| vLLM | Version not pinnedRecipe / cookbook | Documented recipeSource: vllm · models/nvidia/NVIDIA-Nemotron-3-Nano-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-Nano.mdxSource 2: sglang · docs/src/snippets/autoregressive/nemotron3-nano-deployment.jsxReviewed | No supported release indexed | |
Features, dependencies and evidence for SGLang 0.5.19 | ||||
| TensorRT-LLM | 1.2.1Newest indexed | Checkpoint evidenceSource: TensorRT-LLM v1.2.1 · docs/source/models/supported-models.mdReviewed | 1.2.1This release | |
Features, dependencies and evidence for TensorRT-LLM 1.2.1 | ||||