# nvidia/DeepSeek-V4-Flash-nvfp4-DSpark

Model from Hugging Face for text generation: nvidia/DeepSeek-V4-Flash-nvfp4-DSpark · Model Optimizer

## Facts

- Type: LLM
- Task: text-generation
- Framework: Model Optimizer
- License: mit — Permissive open license: commercial use, modification, and redistribution are permitted. (https://huggingface.co/nvidia/DeepSeek-V4-Flash-nvfp4-DSpark/blob/main/LICENSE)
- Source: https://huggingface.co/nvidia/DeepSeek-V4-Flash-nvfp4-DSpark
- Hosting: hosted (7 files)
- Files: 76 listed, none hosted here
- 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: full count and size unknown
- Full repo upstream: 176.2 GB
- Recommended file: 176.2 GB (46 files)
- Download: https://huggingface.co/nvidia/DeepSeek-V4-Flash-nvfp4-DSpark
- Per-file SHA-256: available for 0 of 7 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-nvidia-deepseek-v4-flash-nvfp4-dspark/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: 5687
- Stars: 29
- Card completeness: 89%

## Description

External Hugging Face catalog record for nvidia/DeepSeek-V4-Flash-nvfp4-DSpark. Task: text generation. Library: Model Optimizer. Popularity signal at import: 5,687 downloads and 29 likes.

## Model Card Facts

- Declared license: mit
- Pipeline: text-generation
- Library: Model Optimizer
- Task categories: text-generation
- Paper ids: 2606.19348
- File hints: 16 upstream file samples

## Referenced Data

- Paper: 2606.19348

## File Hints

- .gitattributes (1.6 KB)
- DeepSeek_V4.pdf (4.3 MB) LFS
- LICENSE (1.1 KB)
- README.md (16 KB)
- assets/dsv4_performance.png (977 KB) LFS
- cast_mxfp4_to_nvfp4.log (108 KB)
- config.json (6.9 KB)
- encoding/README.md (7.9 KB)
- encoding/encoding_dsv4.py (27 KB)
- encoding/test_encoding_dsv4.py (3.7 KB)
- encoding/tests/test_input_1.json (2.7 KB)
- encoding/tests/test_input_2.json (526 B)

## Quality Checklist

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

## Safety Notes

- External catalog metadata imported from Hugging Face public API on 2026-09-22T00:08:25.143Z.
- Open license detected as mit.
- Not locally hosted, mirrored, signed, or rescanned by Hugging Bay.
- 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-deepseek-v4-flash-nvfp4-dspark
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-nvidia-deepseek-v4-flash-nvfp4-dspark/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-nvidia-deepseek-v4-flash-nvfp4-dspark/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-nvidia-deepseek-v4-flash-nvfp4-dspark/distribution
- Manifest: not available until files are hosted and release checks pass.
- Request mirror: POST https://huggingbay.xyz/api/artifacts/hf-model-nvidia-deepseek-v4-flash-nvfp4-dspark/mirror-request
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-nvidia-deepseek-v4-flash-nvfp4-dspark/decentralized-fallbacks
