vibe-app/nemotron-3.5-asr-streaming-0.6b-gguf overview
Nemotron 3.5 ASR Streaming 0.6B GGUF Q4 K M GGUF build of NVIDIA Nemotron 3.5 ASR Streaming 0.6B for use by the Vibe app https://github.com/thewh1teagle/vibe .…
Runs locally from ~472.9 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| nemotron-3.5-asr-streaming-0.6b-Q4_K_M.gguf | GGUF | Q4_K_M | 472.9 MB | Download |
Model Details
| Model ID | vibe-app/nemotron-3.5-asr-streaming-0.6b-gguf |
|---|---|
| Author | vibe-app |
| Pipeline | automatic-speech-recognition |
| License | — |
| Base model | nvidia/nemotron-3.5-asr-streaming-0.6b |
| Last modified | 2026-07-11T18:32:59.000Z |
Model README
---
base_model: nvidia/nemotron-3.5-asr-streaming-0.6b
library_name: ggml
tags:
- automatic-speech-recognition
- gguf
- vibe
---
Nemotron 3.5 ASR Streaming 0.6B GGUF
Q4_K_M GGUF build of NVIDIA Nemotron 3.5 ASR Streaming 0.6B for use by the Vibe app.
Vibe uses this model with a Silero VAD model for bounded, long-form transcription.
The upstream model is nvidia/nemotron-3.5-asr-streaming-0.6b. Review its model card and OpenMDW 1.1 license before use.
Run vibe-app/nemotron-3.5-asr-streaming-0.6b-gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models