You can deploy this model and start earning money today!

vokra/
nemotron-3.5-asr-streaming-0.6b

Name: nemotron-3.5-asr-streaming-0.6b
Availability: InStock

vokra

gguf

openmdw-1.1

Views

No views yet

nemotron-3.5-asr-streaming-0.6b (Vokra GGUF)

Converted to the Vokra GGUF format for Vokra, a zero-dependency speech-AI inference runtime.

This is a conversion, not a new model. The weights are the upstream ones; Vokra re-packages them so its runtime can memory-map them directly. Credit for the model belongs upstream — see Source below.

Files

File	Size	SHA-256
`nemotron-3.5-asr-streaming-0.6b.gguf`	2433.8 MB	`1724d8d27dbc36e4e8d7375df881bfc43c0d06474d6b221dea4bc0f4c2d84431`

Usage

bash

# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o nemotron-3.5-asr-streaming-0.6b.gguf \
  https://huggingface.co/vokra/nemotron-3.5-asr-streaming-0.6b/resolve/main/nemotron-3.5-asr-streaming-0.6b.gguf

vokra-cli run --model nemotron-3.5-asr-streaming-0.6b.gguf --input input.wav

Provenance

Field	Value
Architecture	`nemotron_asr_streaming`
Tensors	655
Upstream source	nvidia/nemotron-3.5-asr-streaming-0.6b (NVIDIA Nemotron-3.5 streaming ASR 0.6B, OpenMDW-1.1 permissive)
Upstream licence	`openmdw-1.1`
Licence class	`permissive`
Registry model id	`nemotron-3.5-asr-streaming-0.6b`
Vokra GGUF schema	1
Converted by	vokra-core 0.1.0-alpha.0

Every row above is read out of this file's own vokra.* metadata, so the card cannot claim something the artifact does not carry.

Licence

The weights are distributed under openmdw-1.1, unchanged from upstream. Conversion does not alter the licence, and your obligations run to the upstream author.

Verifying this file

bash

shasum -a 256 nemotron-3.5-asr-streaming-0.6b.gguf
# expect: 1724d8d27dbc36e4e8d7375df881bfc43c0d06474d6b221dea4bc0f4c2d84431