# nvidia/Llama-3_3-Nemotron-Super-49B-v1_5-FP8

Model from Hugging Face for text generation: nvidia/Llama-3_3-Nemotron-Super-49B-v1_5-FP8 · transformers

## Facts

- Type: LLM
- Task: text-generation
- Framework: transformers
- License: nvidia-open-model-license — License: unknown
- Source: https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1_5-FP8
- Hosting: hosted (18 files)
- Files: 18 hosted of 30 listed
- Needs its own code to run: Uses custom model code (configuration_decilm.py). Plain llama.cpp, Ollama and LM Studio commands are not offered for this model unless a GGUF file is listed.
- File counts: "listed" is every file in the source repository; only hosted files download from Hugging Bay, and the download plan lists the files it selects for one download, so its count can differ.
- Hosted here: 18 files, 52 GB
- Full repo upstream: 52 GB
- Recommended file: 52 GB (11 files)
- Parameters: 49B
- Download: https://huggingbay.xyz/artifact/hf-model-nvidia-llama-3-3-nemotron-super-49b-v1-5-fp8/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-nvidia-llama-3-3-nemotron-super-49b-v1-5-fp8/download-plan)
- Per-file SHA-256: available for 18 of 18 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-nvidia-llama-3-3-nemotron-super-49b-v1-5-fp8/files?limit=100
- Run-ready: no (Hugging Bay has not certified a run path for this model; hosted bytes are downloadable and hash-checkable only)
- Peer-assisted fallbacks: 0 verified, 0 pending review
- Downloads: 179201
- Stars: 28
- Card completeness: 92%

## Description

External Hugging Face catalog record for nvidia/Llama-3_3-Nemotron-Super-49B-v1_5-FP8. Task: text generation. Library: transformers. Languages: en. Popularity signal at import: 179,201 downloads and 28 likes.

## Model Card Facts

- Declared license: other
- Pipeline: text-generation
- Library: transformers
- Task categories: text-generation
- Languages: en
- Paper ids: 2411.19146, 2505.00949, 2502.00203
- File hints: 16 upstream file samples

## Referenced Data

- Paper: 2411.19146
- Paper: 2505.00949
- Paper: 2502.00203

## File Hints

- .gitattributes (1.6 KB)
- BIAS.md (208 B)
- EXPLAINABILITY.md (2.9 KB)
- PRIVACY.md (514 B)
- README.md (17 KB)
- SAFETY&SECURITY.md (920 B)
- accuracy_chart.png (179 KB) LFS
- block_config.py (4.2 KB)
- config.json (36 KB)
- configuration_decilm.py (2.5 KB)
- generation_config.json (176 B)
- hf_quant_config.json (266 B)

## Quality Checklist

- Summary: passed
- Description: passed
- Model card metadata: passed
- License: review
- Provenance: passed
- File inventory: passed
- Hosted bytes: passed
- Scan result: passed
- Manifest signature: passed

## Safety Notes

- External catalog metadata imported from Hugging Face public API on 2026-09-21T01:06:23.839Z.
- Upstream license: other. Mirror admission policy: permissive (owner policy; no license rights inferred).
- Not a run kit: hosted, hash-checked bytes only; run readiness is not certified for this model yet.

## Actions

- Web: https://huggingbay.xyz/artifact/hf-model-nvidia-llama-3-3-nemotron-super-49b-v1-5-fp8
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-nvidia-llama-3-3-nemotron-super-49b-v1-5-fp8/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-nvidia-llama-3-3-nemotron-super-49b-v1-5-fp8/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-nvidia-llama-3-3-nemotron-super-49b-v1-5-fp8/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-nvidia-llama-3-3-nemotron-super-49b-v1-5-fp8
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-nvidia-llama-3-3-nemotron-super-49b-v1-5-fp8/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-nvidia-llama-3-3-nemotron-super-49b-v1-5-fp8&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-nvidia-llama-3-3-nemotron-super-49b-v1-5-fp8/decentralized-fallbacks