Nemotron Speech Streaming EN needs about 1.0 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 0.5 GB (Q4_K_M) to 2.5 GB (F32).
600M‑parameter English ASR model for low‑latency streaming
Nemotron Speech Streaming EN is a 0.6 B parameter model that transcribes English speech into text with punctuation and capitalization. It uses a cache‑aware FastConformer‑RNNT architecture for efficient streaming and high throughput. The model supports configurable chunk sizes for low‑latency voice applications.
Good at
- Low‑latency streaming ASR
- High‑throughput batch transcription
- Native punctuation and capitalization
Limits
- No vision support
- Requires 8 k context for estimates
- License is NVIDIA Open Model License
Best for
- Voice assistants needing real‑time transcription
- Batch processing of large audio libraries
- Transcribing call center recordings
Who it’s for. Developers building voice‑enabled applications that require accurate, real‑time English transcription. The model is suitable for both offline and streaming use cases where punctuation and capitalization are needed.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.5 GB | 1.0 GB | Fits | Get file → | |
| Q5_K_M | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q6_K | 0.6 GB | 1.2 GB | Fits | Get file → | |
| Q8_0 | 0.7 GB | 1.3 GB | Fits | Get file → | |
| F16 | 1.2 GB | 1.9 GB | Fits | Get file → | |
| F32 | 2.5 GB | 3.3 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.48 GB, ~1 GB RAM). For 16 GB VRAM, Q5_K_M or Q6_K (0.54–0.60 GB) provide a balance of speed and memory. Higher precision F16 or F32 increases memory to 1.9–3.3 GB and is only recommended if extra VRAM is available.
What GPU do you need for Nemotron Speech Streaming EN?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is F32 (2.5 GB file, about 3.3 GB in use).
Which Nemotron Speech Streaming EN quant should you choose?
Q4_K_M is the usual starting point for Nemotron Speech Streaming EN: it balances file size and quality well. Here it is a 0.5 GB file.
The Q8_0 file is 0.7 GB, about 1.5 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Nemotron Speech Streaming EN
How much VRAM does Nemotron Speech Streaming EN need?
About 1.0 GB at Q4_K_M with an 8K context window. That is the 0.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Nemotron Speech Streaming EN on an 8 GB GPU?
Yes, with F32: the 2.5 GB file needs about 3.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Nemotron Speech Streaming EN GGUF?
It depends on the quant: Q4_K_M is 0.5 GB, Q5_K_M is 0.5 GB, Q6_K is 0.6 GB, Q8_0 is 0.7 GB, F16 is 1.2 GB, F32 is 2.5 GB.
Where can I download Nemotron Speech Streaming EN GGUF?
The files are on Hugging Face in the handy-computer/nemotron-speech-streaming-en-0.6b-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Nemotron Speech Streaming EN use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Nemotron Speech Streaming on 8 GB VRAM?
Yes, the Q4_K_M quantization uses about 1 GB of RAM at 8 k context, fitting comfortably on 8 GB VRAM.
Does the model support other languages?
The current release is English only; multilingual support is planned in a future 40‑language version.
What chunk sizes can I use for streaming?
Configurable chunk sizes include 80 ms, 160 ms, 560 ms, and 1120 ms for low‑latency streaming.