Blog - Turing Pi

October 26, 2026

Whisper vs Parakeet on Jetson Orin Nano: Benchmarks

A speech-to-text model might recognize clean recordings perfectly and still be the wrong choice for an 8GB Jetson Orin Nano. Conversational speech is harder, processing speed varies widely, and the largest models can leave little memory for other services. We tested five OpenAI Whisper configurations and two NVIDIA Parakeet configurations for automatic speech recognition (ASR) […]

October 23, 2026

YOLO on Jetson Orin Nano: FPS, Latency and TensorRT Benchmarks

YOLO11n ran 1.83× faster in serial replay with TensorRT than with PyTorch FP32 on our Jetson Orin Nano 8GB. In live runs receiving about 20 camera frames per second, TensorRT recorded a median per-run p99 decision latency of 39.63 ms, compared with 98.82 ms for PyTorch FP32. Processed FPS alone largely hid that difference. These tests on Turing Pi 2.5 […]

October 19, 2026

How Voice Assistants Work and Why They Feel Slow

You ask a voice assistant to turn off the kitchen lights. It hears the words correctly, pauses, then answers. You start correcting it halfway through the reply, but it keeps talking. The speech recognition worked. The conversation did not. To understand how voice assistants work, separate two jobs: understanding a request and managing the conversation […]

October 17, 2026

Frigate on Jetson Orin Nano: Camera Tests on Turing Pi 2.5

We tested Frigate on a Jetson Orin Nano Super installed in Turing Pi 2.5, using a USB webcam and NVMe storage to capture video, detect people and record events locally. Then we measured the camera pipeline at three video rates to find out where the CPU time and recording space went. The core system worked: Frigate […]

October 13, 2026

Why Local LLMs Are Fast or Slow: Tokens per Second, Memory Bandwidth, Prefill and Decode

In our Jetson Orin Nano 8GB benchmarks, Qwen3 1.7B processed prompts at 1,408 tokens per second but generated answers at about 39 tokens per second. Both numbers came from the same model and device. They measured different work. Understanding that difference helps explain why a local LLM can respond quickly to a short question yet […]

October 10, 2026

Distributed ROS 2 on Jetson Orin Nano and Turing Pi 2.5: Raw vs JPEG vs Detections

When a Jetson processes camera images and another computer uses the results, what should cross the network: the images, a compressed preview, or just the detections? We compared all three on Turing Pi 2.5 using ROS 2 Jazzy. A Jetson Orin Nano 8GB handled object detection, an RK1 received the results, and a second RK1 […]

October 1, 2026

Jetson Orin Nano Dev Kit vs Turing Pi 2.5: Same Module, Same NVMe, Measured

This Jetson Orin Nano Dev Kit vs Turing Pi 2.5 comparison starts with one important constraint: moving the Jetson between carriers does not give the module a faster GPU, more memory, or a higher nominal compute ceiling. The CPU, GPU, Tensor Cores, and 8GB of LPDDR5 live on the Jetson module itself. What changes is […]

September 26, 2026

What LLMs Actually Fit on a Jetson Orin Nano 8GB? Models, Context, and Runtimes Tested

An 8GB Jetson Orin Nano looks like a tight target for modern local LLMs. In practice, it can stretch much further than the model-file size alone suggests. In our standardized benchmark pass on Turing Pi 2.5, all seven Q4_K_M models we tested loaded with full logged GPU layer placement at a 4,096-token context setting, including […]

September 21, 2026

AI Is Becoming an Inference Problem, Not Just a Training Problem

For years, the most visible question in AI hardware was how much compute it took to train the next model. Bigger clusters, faster accelerators, and longer training runs became shorthand for progress. But a trained model has no practical value until people and applications can use it. That second task is inference. Every generated answer, […]

September 16, 2026

Run Ollama on Jetson Orin Nano: Build a Local AI Server on Turing Pi 2.5

The previous guide, Preparing NVIDIA Jetson as an AI Node on Turing Pi 2.5, established the operational foundation for a long-running accelerated node. Docker can access the GPU, models and application data have predictable locations on the NVMe, the Jetson has a stable network identity, and basic logging and health checks are in place. This […]