nemotron 3.5 asr streaming needs about 1.0 GB of memory at Q4_K (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.4 GB (Q4_K) to 1.3 GB (F16).
Nemotron 3.5 ASR: 600 M‑parameter multilingual streaming speech recognizer
Nemotron 3.5 ASR is a 0.638 billion‑parameter model that transcribes speech into text with native punctuation and capitalization. It supports 40 language‑locales via language‑ID prompt conditioning and offers low‑latency streaming with cache‑aware FastConformer‑RNNT architecture.
Good at
- Multilingual transcription of 40 locales
- Low‑latency streaming with cache‑aware design
- High throughput for batch workloads
Limits
- No vision support
- Requires 8 k context for memory estimates
- OpenMDW‑1.1 license
Best for
- Voice‑assistant back‑ends
- Real‑time transcription services
- Batch ASR pipelines
Who it’s for. Developers building commercial speech‑to‑text applications that need a single model for many languages and efficient streaming. The model is ready for production use and supports dynamic runtime flexibility.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 0.4 GB | 1.0 GB | Fits | Get file → | |
| F16 | 1.3 GB | 1.9 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K (0.41 GB file, ~1 GB memory at 8 k context). For 16 GB VRAM, F16 (1.29 GB file, ~1.9 GB memory at 8 k context) provides higher precision. Memory estimates are approximate.
What GPU do you need for nemotron 3.5 asr streaming?
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 F16 (1.3 GB file, about 1.9 GB in use).
Which nemotron 3.5 asr streaming quant should you choose?
Q4_K (0.4 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about nemotron 3.5 asr streaming
How much VRAM does nemotron 3.5 asr streaming need?
About 1.0 GB at Q4_K with an 8K context window. That is the 0.4 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 3.5 asr streaming on an 8 GB GPU?
Yes, with F16: the 1.3 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of nemotron 3.5 asr streaming GGUF?
It depends on the quant: Q4_K is 0.4 GB, F16 is 1.3 GB.
Where can I download nemotron 3.5 asr streaming GGUF?
The files are on Hugging Face in the cstr/nemotron-3.5-asr-streaming-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 3.5 asr streaming use?
Hugging Face lists the license as openmdw-1.1. 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 3.5 ASR on 8 GB VRAM?
Yes, the Q4_K quantization file is 0.41 GB and requires about 1 GB of VRAM at 8 k context.
Does the model support vision tasks?
No, it is an ASR model with no vision capabilities.
What license applies to this model?
The model is released under the OpenMDW‑1.1 license, which allows commercial use.