NVIDIA-Nemotron-3-Nano-4B-FP8
Support summary
NVIDIA-Nemotron-3-Nano-4B-FP8 is a checkpoint published by NVIDIA, built on the NemotronHForCausalLM architecture. Official recipes or cookbooks cover vLLM, without pinning a stable release. TensorRT-LLM lists its architecture, but not this exact checkpoint.
- Documented quantization
- FP8
- 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
- 4B
- Tensor types
- F32, BF16, F8_E4M3
- Configured context
- 262,144 tokens
- Languages
- en
- Base models
- nvidia/NVIDIA-Nemotron-3-Nano-4B-FP8
- Weight access
- Public
- Repository created
- 2026-03-12
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-4B-BF16.yamlReviewed | No supported release indexed | |
Features, dependencies and evidence for vLLM 0.28.0 | ||||
| SGLang | 0.5.19Newest indexed | No matching evidence curated | 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 | ||||