NelsaHost

Hardware AI Models Compatibility Compare

search Login

Can I run Whisper Small on NVIDIA Jetson AGX Orin 32GB?

check_circle

Perfect

Yes, you can run this model!

GPU VRAM

32.0GB

Required

0.5GB

Headroom

+31.5GB

VRAM Usage

0GB 2% used 32.0GB

Performance Estimate

Tokens/sec ~90.0

Batch size 32

info Technical Analysis

NVIDIA Jetson AGX Orin 32GB provides excellent compatibility with Whisper Small. With 32.0GB of VRAM and only 0.5GB required, you have 31.5GB of headroom for comfortable inference. This allows for extended context lengths, batch processing, and smooth operation.

lightbulb Recommendation

You can run Whisper Small on NVIDIA Jetson AGX Orin 32GB without any compromises. Consider using full context length and larger batch sizes for optimal throughput.

tune Recommended Settings

Batch_Size

Context_Length

448

Inference_Framework

llama.cpp or vLLM

help Frequently Asked Questions

Can I run Whisper Small on NVIDIA Jetson AGX Orin 32GB? expand_more

NVIDIA Jetson AGX Orin 32GB has 32.0GB VRAM, which provides 31.5GB of headroom beyond the 0.5GB required by Whisper Small (0.24B). This is plenty of room for comfortable inference with room for KV cache, batching, and extended context lengths.

How much VRAM does Whisper Small need? expand_more

Whisper Small requires approximately 0.5GB of VRAM.

What performance can I expect? expand_more

Estimated 90 tokens per second.