NVIDIA-Nemotron-3.5-Transcribe-30B-A4B
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4BNew to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
NVIDIA-Nemotron-3.5-Transcribe-30B-A4B is an open-weight speech recognition model from nvidia, published on Hugging Face in October 2026. It has 33.7B parameters and is released under a custom license (see the model card).
HardwareLink to this section
At full FP16 precision the weights need about 67 GB of memory; 8-bit quantization brings that to roughly 36 GB. Check the VRAM tiers above to see which GPUs fit it.
PopularityLink to this section
NVIDIA-Nemotron-3.5-Transcribe-30B-A4B had 76,196 downloads on Hugging Face in the last month and has 3,241 likes.
Run it locallyLink to this section
The weights are on Hugging Face and load with NVIDIA NeMo. Follow the model card for the exact setup and license terms.
Frequently asked
Quick answers to common questions
How much VRAM does NVIDIA-Nemotron-3.5-Transcribe-30B-A4B need?
NVIDIA-Nemotron-3.5-Transcribe-30B-A4B with 33.7B parameters needs approximately 20 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.
Is NVIDIA-Nemotron-3.5-Transcribe-30B-A4B better than other nvidia models?
NVIDIA-Nemotron-3.5-Transcribe-30B-A4B has 33.7B parameters with 262,144 context - a strong choice for speech-recognition.
What license is NVIDIA-Nemotron-3.5-Transcribe-30B-A4B under?
NVIDIA-Nemotron-3.5-Transcribe-30B-A4B is released under the Other license, making it suitable for most commercial and personal projects.
What hardware runs NVIDIA-Nemotron-3.5-Transcribe-30B-A4B well?
With 33.7B parameters, NVIDIA-Nemotron-3.5-Transcribe-30B-A4B requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.
What is the best quantization for NVIDIA-Nemotron-3.5-Transcribe-30B-A4B?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~24 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.
How long can NVIDIA-Nemotron-3.5-Transcribe-30B-A4B's context window handle?
NVIDIA-Nemotron-3.5-Transcribe-30B-A4B supports a 262,144-token context window - enough for very long documents, codebases, or multi-turn conversations. Real-world usable context may vary by implementation.
What models compete with NVIDIA-Nemotron-3.5-Transcribe-30B-A4B?
NVIDIA-Nemotron-3.5-Transcribe-30B-A4B competes with other 17B–51B. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.
Nearby options
Similar models and compatible hardware by spec