NE

nemotron 3.5 asr streaming 0.6b

NemotronGGUF by cstrUpdated 2026-08-30
Download on Hugging Face
Parameters638M
Context—
Layers—
Architecturenemotron
Smallest quant0.4 GB
Quick answer

nemotron 3.5 asr streaming 0.6b needs about 1.3 GB of memory at Q8_0 (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.4 GB (Q4_K) to 1.3 GB (F16).

Nemotron 3.5 ASR: 0.6B multilingual streaming speech recognition

Nemotron 3.5 ASR is a 0.6B parameter model that transcribes speech into text with punctuation and capitalization. It supports 40 language‑locales via language‑ID prompt conditioning and is optimized for low‑latency streaming and high‑throughput batch workloads.

Good at

  • Multilingual transcription of 40 language‑locales
  • Low‑latency streaming with cache‑aware FastConformer
  • High throughput for batch processing

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • OpenMDW‑1.1 license limits commercial use to permissive terms

Best for

  • Voice assistants needing multilingual support
  • Batch ASR pipelines for large datasets
  • Real‑time transcription in multi‑language environments

Who it’s for. Developers building multilingual voice agents or batch transcription services that require a single model for many languages. The model is ready for commercial deployment under the OpenMDW‑1.1 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K0.4 GB 1.0 GB
Fits Get file →
Q8_00.7 GB 1.3 GB
Fits Get file →
F161.3 GB 1.9 GB
Fits Get file →

For 8GB VRAM use Q4_K (0.41 GB, ~1 GB memory at 8k context). For 12GB VRAM use Q8_0 (0.69 GB, ~1.3 GB memory). For 16GB VRAM use F16 (1.29 GB, ~1.9 GB memory). Estimates are approximate.

What GPU do you need for nemotron 3.5 asr streaming 0.6b?

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 0.6b quant should you choose?

Q8_0 (0.7 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

If memory is tight, the smallest file is Q4_K at 0.4 GB, with the quality trade-offs that come with fewer bits. 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

Architecturenemotron
Parameters638M

Source

Quantized bycstr
FamilyNemotron
Downloads (HF)898
Last updated2026-08-30

Frequently asked questions about nemotron 3.5 asr streaming 0.6b

How much VRAM does nemotron 3.5 asr streaming 0.6b need?

About 1.3 GB at Q8_0 with an 8K context window. That is the 0.7 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 0.6b 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 0.6b GGUF?

It depends on the quant: Q4_K is 0.4 GB, Q8_0 is 0.7 GB, F16 is 1.3 GB.

Where can I download nemotron 3.5 asr streaming 0.6b GGUF?

The files are on Hugging Face in the cstr/nemotron-3.5-asr-streaming-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 3.5 asr streaming 0.6b 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 8GB VRAM?

Yes, the Q4_K quantized model is 0.41 GB and requires about 1 GB of VRAM at 8k context, fitting within 8GB.

Does the model support vision tasks?

No, Nemotron 3.5 ASR is an audio-only model with no vision capabilities.

What license applies to this model?

The model is released under the OpenMDW‑1.1 license, which is permissive for commercial use.

Other GGUFs of nemotron-3.5-asr-streaming-0.6b

Similar models

Browse all →

More from cstr

All by cstr →

More Nemotron models

All Nemotron →

Other tiny models

All tiny models →