nvidia/Nemotron-Cascade-2-30B-A3B
nvidia/Nemotron-Cascade-2-30B-A3B is an open-weights language model for text generation under the other license (58.8 GB), released Jul 9, 2026. Hosted open-weights model — 20 files carry published SHA-256 checksums you can re-hash. 20 Hugging Bay hosted files
- License
- other
- Task
- text generation
- Size
- 58.8 GB
- Recommended file
- 58.8 GB (13 files)
- Parameters
- 30B (3B active)
- Files
- 20 hosted of 20 listed
- Download
- License review needed before download (20 hosted files)
- Released
- Updated on Hugging Bay
FAQ
What is nvidia/Nemotron-Cascade-2-30B-A3B?
nvidia/Nemotron-Cascade-2-30B-A3B is an open-weights language model for text generation published by nvidia, released Jul 9, 2026. Model from Hugging Face for text generation: nvidia/Nemotron-Cascade-2-30B-A3B · transformers
What license does nvidia/Nemotron-Cascade-2-30B-A3B use, and can I use it commercially?
It is released under the other license. Commercial-use terms are not established. No usable license information. Treat as all-rights-reserved until the upstream license is confirmed.
How big is nvidia/Nemotron-Cascade-2-30B-A3B?
nvidia/Nemotron-Cascade-2-30B-A3B has 30B parameters (3B active per token). The total download is 58.8 GB; the recommended download, a 13-file weight set, is 58.8 GB.
Where can I download nvidia/Nemotron-Cascade-2-30B-A3B?
Hugging Bay hosts 20 of 20 files for this model, each with a published SHA-256 checksum. Total size: 58.8 GB. The original release is at https://huggingface.co/nvidia/Nemotron-Cascade-2-30B-A3B.
Has nvidia/Nemotron-Cascade-2-30B-A3B been scanned for unsafe files?
Source scan status: passed. 20 hosted files carry a published SHA-256 you can re-hash. The machine-readable verdict is at /api/artifacts/hf-model-nvidia-nemotron-cascade-2-30b-a3b/safety on Hugging Bay.
Does nvidia/Nemotron-Cascade-2-30B-A3B run on an RTX 4090 (24GB)?
nvidia/Nemotron-Cascade-2-30B-A3B needs ~69.82 GB of memory (weights + KV cache at 8192 tokens); that is more than the 24 GB on an RTX 4090 (24GB), so it does not fit. Smallest quant that fits: Q2_K. Computed from stated size and quant, not a runtime guarantee.
Does nvidia/Nemotron-Cascade-2-30B-A3B run on an RTX 3090 (24GB)?
nvidia/Nemotron-Cascade-2-30B-A3B needs ~69.82 GB of memory (weights + KV cache at 8192 tokens); that is more than the 24 GB on an RTX 3090 (24GB), so it does not fit. Smallest quant that fits: Q2_K. Computed from stated size and quant, not a runtime guarantee.
Does nvidia/Nemotron-Cascade-2-30B-A3B run on an A100 (80GB)?
nvidia/Nemotron-Cascade-2-30B-A3B needs ~69.82 GB, which is within the 80 GB on an A100 (80GB) by memory capacity (~10.18 GB headroom). Computed from stated size and quant, not a runtime guarantee.
Does nvidia/Nemotron-Cascade-2-30B-A3B run on a 16GB laptop (no dedicated GPU)?
nvidia/Nemotron-Cascade-2-30B-A3B needs ~69.82 GB of memory (weights + KV cache at 8192 tokens); that is more than the 16 GB on a 16GB laptop (no dedicated GPU), so it does not fit. Smallest quant that fits: Q2_K. Computed from stated size and quant, not a runtime guarantee.
Does nvidia/Nemotron-Cascade-2-30B-A3B run on an 8GB laptop (no dedicated GPU)?
nvidia/Nemotron-Cascade-2-30B-A3B needs ~69.82 GB of memory (weights + KV cache at 8192 tokens); that is more than the 8 GB on an 8GB laptop (no dedicated GPU), so it does not fit. Smallest quant that fits: none. Computed from stated size and quant, not a runtime guarantee.
About this artifact
External Hugging Face catalog record for nvidia/Nemotron-Cascade-2-30B-A3B. Task: text generation. Library: transformers. Languages: en. Popularity signal at import: 15,660 downloads and 527 likes. Files are listed for discovery and verification context; Hugging Bay serves local downloads only after explicit mirror review, scanning, hashing, and signing.
Hosted file inventory
File inventory only. Individually hashed hosted files may be available, but bundle completeness, verification, and runtime state are unknown.
- Hosted files
- 20 of 20
- Reviewed peer-assisted fallbacks
- 0
- Trust bundle
- Trust-bundle JSON
- Review summary
- Review-summary JSON
- Distribution
- Reviewed peer-fallback JSON
Run status
License review needed first — License: other — needs a human review first. No download until it's cleared.
Detailed evidence for the selected file set
This detail applies to the selected file set, not every file in the repository.
- Executable state
- complete-bytes
- Evidence timestamp
- 2026-09-21T11:01:53.721Z
- Selected representation
- rep-b3186540f5fe1cdfe75b5deca4b0b2444ecd04b3661e438e6c8459d087cf9dd1
- Complete bytes
- yes
- Complete kit
- no
- Verification
- not verified
- Run ready
- not established
- Files
- View file metadata
Bay Run
Try It Now unavailable
Bay Run does not publish a serving contract for this exact artifact and Hugging Bay will not invent one.
Mint a Pin unavailable
Bay Run does not publish a serving contract for this exact artifact and Hugging Bay will not invent one.
Guard before generate
Add Bay Run's provider-neutral coprocessor to your own generation pipeline. It checks decision.action before your generator runs.
npm install @huggingbay/coprocessor · Install @huggingbay/coprocessor
This handoff wraps your caller-owned generator. It does not run this catalog artifact, make it a Bay Run Pin, or change its serving or verification state.
Open official source
- License: fail - other
- Provenance: pass - nvidia/Nemotron-Cascade-2-30B-A3B
- Scan: pass - passed
- Hosted files: warn - 20/20 repository files hosted; selected representation evaluated separately
- Byte manifest integrity: warn - not final yet
Machine-readable card
Open interactive artifact page
Evidence details
- Demand
- 16K upstream downloads
- Trust
- Unknown
- Trusted download
- File inventory only
- Run fit
- Canonical selected-byte evidence recorded; public obtain path unavailable
- Scan status
- passed
- Executable state
- complete-bytes
- Evidence timestamp
- 2026-09-21T11:01:53.721Z
- Declared license
- other
- Pipeline
- text-generation
- Library
- transformers
- Task categories
- text-generation
- Languages
- en
- Paper ids
- 2603.19220
- File hints
- 16 upstream file samples