Qwen3.8-Flash-Next-FP4-Local

Model facts

Hub id

nvidia/Qwen3.8-Flash-Next-FP4-Local

Likes

208

Downloads (last 30 days)

4,876

Task

Image and text to text

Library

Not given

Parameters

96.5B (96,486,615,005)

License

Nvidia open model agreement

Access

Open download

Author

nvidia · Organization

Languages

Not given

Created

Oct 8, 2026

Last modified

Oct 15, 2026

Base model

• Quantized version of Qwen/Qwen3.8-Flash-Next

Rank #2,115 of 4,320 models in AI on Hugging Face, by likes. Data from the Hugging Face Hub API, fetched Oct 18, 2026. Likes measure popularity, not quality or safety. Downloads are for the last 30 days, as the Hub reports them; counts change daily. A listing is not an endorsement. How this list is made

More models from nvidia

• 59

  Rank 59: nvidia/LocateAnything-3B

  3,120 likes392,375 downloads in the last 30 daysImage and text to text3.83B parametersNvidia license

• 74

  Rank 74: nvidia/personaplex-7b-v1

  2,844 likes134,897 downloads in the last 30 daysAudio to audio8.37B parametersNvidia open model licenseGated

• 120

  Rank 120: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF

  2,071 likes23,238 downloads in the last 30 daysText generation70.6B parametersLlama 3.1 license

• 195

  Rank 195: nvidia/parakeet-tdt-0.6b-v2

  1,570 likes193,654 downloads in the last 30 daysSpeech recognitionCC BY 4.0

• 286

  Rank 286: nvidia/nemotron-3.5-asr-streaming-0.6b

  1,216 likes1,218,333 downloads in the last 30 daysSpeech recognition638M parametersOpenmdw 1.1

• 293

  Rank 293: nvidia/parakeet-tdt-0.6b-v3

  1,205 likes626,564 downloads in the last 30 daysSpeech recognition627M parametersCC BY 4.0