NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4
Support summary
NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 is a checkpoint published by NVIDIA, built on the NemotronHForCausalLM architecture. SGLang 0.5.19, the newest indexed SGLang release, documents support. Official recipes or cookbooks cover vLLM, without pinning a stable release. TensorRT-LLM lists its architecture, but not this exact checkpoint.
SGLang documents support in 13 of 13 indexed releases, from 0.5.10 to 0.5.19.
- Documented quantization
- NVFP4
- Documented features
- Multi-token prediction, Prefix caching, Reasoning parsers, Speculative decoding, Tensor parallelism, 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
- 67.2B
- Tensor types
- F32, BF16, F8_E4M3, U8
- Quantization
- modelopt
- Configured context
- 262,144 tokens
- Languages
- en, fr, es, it, de, ja, zh
- Weight access
- Public
- Repository created
- 2026-03-10
Model notes and sources
- SGLang v0.5.19 · docs/docs/supported-models/generative_models.mdx · 3 indexed revisions, v0.5.17 to v0.5.19
- SGLang v0.5.16 · docs_new/docs/supported-models/generative_models.mdx · 8 indexed revisions, v0.5.11 to v0.5.16
- SGLang v0.5.15.post1 · docs/supported_models/text_generation/generative_models.md · 9 indexed revisions, v0.5.10 to v0.5.15.post1
- nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 · publisher model card
- nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 · Hugging Face metadata
- nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 · publisher configuration
- vllm · models/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16.yaml
- sglang · docs/src/snippets/autoregressive/nemotron3-super-deployment.jsx
- 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-Super-120B-A12B-BF16.yamlReviewed | No supported release indexed | |
Features, dependencies and evidence for vLLM 0.28.0 | ||||
| SGLang | 0.5.19Newest indexed | Checkpoint evidenceSource: SGLang v0.5.19 · docs/docs/supported-models/generative_models.mdxReviewed | 0.5.19This release | |
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 | ||||