nemotron-3.5-asr-streaming-0.6b
nvidiaOtheraudio

nemotron-3.5-asr-streaming-0.6b

Updated Nov 21, 2026
Parameters
640M
License
Other
Q4 GGUF
0.5 GB
Updated
Nov 21, 2026

Q4 GGUF download: handy-computer/nemotron-3.5-asr-streaming-0.6b-gguf - 0.5 GB on disk, read 2026-11-19. VRAM figures above are estimates; this is the actual file size.

Will it run on your hardware?

Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest

Runs on your 24 GB - best at FP16
4 of 4 quantizations fit nemotron-3.5-asr-streaming-0.6b with real runtime overhead.
Q4_K_M
1 GB
Q5_K_M
1 GB
Q8_0
1 GB
FP16
1 GB
fits tight too big

Need an exact figure for your context length? Use the VRAM calculator.

Run it locally

Copy-paste - running in under a minute

vLLMOpenAI-compatible API
vllm serve nvidia/nemotron-3.5-asr-streaming-0.6b

New to this? Start with Ollama · serve to many users with vLLM.

Deep dive

Notes, sources, and the full write-up

nemotron-3.5-asr-streaming-0.6b is an open-weight speech recognition model published by nvidia on Hugging Face in May 2026, with 640M parameters under a custom license (read the model card before commercial use).

Among the 25 speech recognition models in this directory it ranks 12th by monthly Hugging Face downloads, and 11 of the others are larger.

HardwareLink to this section

Unquantized FP16 weights take about 1 GB; 8-bit brings that to ~1 GB and 4-bit (Q4_K_M) to ~1 GB, before activations and any context or image buffers. At this size it runs on almost any recent GPU, on Apple Silicon, and usable on a modern CPU. Check exact numbers for your card with the VRAM calculator.

Similar speech recognition modelsLink to this section

PopularityLink to this section

nemotron-3.5-asr-streaming-0.6b was downloaded 448,774 times on Hugging Face in the last month (4,416,286 all-time) and has 1,286 likes.

Run it locallyLink to this section

Weights and usage instructions are on the nvidia/nemotron-3.5-asr-streaming-0.6b model card; it loads with NVIDIA NeMo.

Local runtimes that fit this model:

  • ollama - one-command local inference once a GGUF build is available
  • llama-cpp - the GGUF engine underneath most local runners
  • lm-studio - a desktop app for downloading and chatting with GGUF models
  • vllm - high-throughput serving on NVIDIA GPUs

PaperLink to this section

From the community

What users are saying

“@altunenes - try fine tuning and adapting the languages balance : Blog - https://huggingface.co/blog/nvidia/fine-tuning-nemotron-35-asr Repo - https://github.com/nvidia-riva/tutorials/blob/main/asr-finetune-nemotron-3.5-asr-streaming-prompt.ipynb”

“Yes. The Nemotron ASR model already outputs alignment information that can be converted into timestamps for words or tokens, so generating a timestamped transcript is possible from the inference output. However, speaker IDs are not part of the Nemotron ASR output.”

“Nemotron ASR uses a FastConformer-RNNT architecture, which is fundamentally different from the autoregressive transformer decoder architecture that vLLM is designed to serve.”

Frequently asked

Quick answers to common questions

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

nemotron-3.5-asr-streaming-0.6b with 640M parameters needs approximately 1 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.

Is nemotron-3.5-asr-streaming-0.6b better than other nvidia models?

nemotron-3.5-asr-streaming-0.6b has 640M parameters - a strong choice for speech-recognition.

What license is nemotron-3.5-asr-streaming-0.6b under?

nemotron-3.5-asr-streaming-0.6b is released under the Other license, making it suitable for most commercial and personal projects.

What hardware runs nemotron-3.5-asr-streaming-0.6b well?

With 640M parameters, nemotron-3.5-asr-streaming-0.6b is small enough for most consumer GPUs, Apple Silicon Macs, and many CPUs. Check our hardware directory for specific recommendations.

What is the best quantization for nemotron-3.5-asr-streaming-0.6b?

Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~1 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.

What models compete with nemotron-3.5-asr-streaming-0.6b?

nemotron-3.5-asr-streaming-0.6b competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.

Nearby options

Similar models and compatible hardware by spec