Dev kit · current · data 2026-10-15

NVIDIA Jetson Orin Nano Super Developer Kit for local AI.

Name: NVIDIA Jetson Orin Nano Super Developer Kit
Brand: NVIDIA

With 8 GB it runs Qwen3.5 4B (needs 5.8 GB). 19 models fit. Published speed: Llama 3.2 3B at 43.07 tokens/sec.

Memory8 GB

Shared between CPU and graphics.

Bandwidth102 GB/s

Higher means faster answers.

PriceFrom about $399

As of 2026-10-12. Check before buying.

Which models fit

By memory option.

Usable: 75% on Macs and shared-memory PCs, VRAM minus 1 GB on graphics cards (estimates).
Memory	Usable	Models that fit	Best three
8 GB	6 GB	19	Qwen3.5 4B (5.8 GB), MiniCPM5 2B (3.9 GB), Granite 4.2 3B (4.5 GB)

Speed

Published speeds.

Measured by others, with sources. Not our tests.

Model	Tokens/sec	Engine	Setup	Source
Llama 3.2 3B	43.07	MLC · INT4	—	vendor-measured · 2026-10-12
Qwen2.5 3B	22.6	Ollama · Q4 (Ollama default)	—	community-measured · 2026-10-12

Questions

Short answers.

What is the best local LLM for the NVIDIA Jetson Orin Nano Super Developer Kit?: With 8 GB, Qwen3.5 4B (needs 5.8 GB, AA 13.1). 19 of 124 models fit.
How fast is the NVIDIA Jetson Orin Nano Super Developer Kit for local AI?: Published: Llama 3.2 3B at 43.07 tokens/sec (MLC, ); Qwen2.5 3B at 22.6 tokens/sec (Ollama, ). These are other people's measurements, not ours.
How much does the NVIDIA Jetson Orin Nano Super Developer Kit cost?: From about $399 (as of 2026-10-12). 2026 prices are inflated by the memory-chip shortage; check before buying.

Specs from ComputingForGeeks – Jetson Orin Nano Super vs AI HAT+ 2 vs Hailo-10H (prices/benchmarks checked 2026-10-12) (2026-10-12). Prices are approximate and dated; 2026 prices are inflated by the memory-chip shortage.

AGENT VIEW · text/markdown · or send Accept: text/markdown

# NVIDIA Jetson Orin Nano Super Developer Kit for local AI

URL: https://insidethemachine.ai/machines/jetson-orin-nano-super
Type: Dev kit. Chip: Orin Nano (Ampere, 1024 cores). Memory: unified, options 8 GB. Bandwidth: 102 GB/s. Spec source: https://computingforgeeks.com/edge-llm-jetson-orin-vs-ai-hat-2-vs-hailo-10h/ (2026-10-12).
Price: from about $399 (2026-10-12, approximate). Status: current.

## Which models fit

| memory GB | usable GB | models that fit | best 3 |
|---|---|---|---|
| 8 | 6 | 19 | Qwen3.5 4B (5.8 GB), MiniCPM5 2B (3.9 GB), Granite 4.2 3B (4.5 GB) |

## Published speeds (not our tests)

- Llama 3.2 3B: 43.07 tok/s decode (MLC, INT4, , vendor-measured) https://computingforgeeks.com/edge-llm-jetson-orin-vs-ai-hat-2-vs-hailo-10h/ (2026-10-12)
- Qwen2.5 3B: 22.6 tok/s decode (Ollama, Q4 (Ollama default), , community-measured) https://computingforgeeks.com/edge-llm-jetson-orin-vs-ai-hat-2-vs-hailo-10h/ (2026-10-12)

## Questions

**What is the best local LLM for the NVIDIA Jetson Orin Nano Super Developer Kit?**
With 8 GB, Qwen3.5 4B (needs 5.8 GB, AA 13.1). 19 of 124 models fit.

**How fast is the NVIDIA Jetson Orin Nano Super Developer Kit for local AI?**
Published: Llama 3.2 3B at 43.07 tokens/sec (MLC, ); Qwen2.5 3B at 22.6 tokens/sec (Ollama, ). These are other people's measurements, not ours.

**How much does the NVIDIA Jetson Orin Nano Super Developer Kit cost?**
From about $399 (as of 2026-10-12). 2026 prices are inflated by the memory-chip shortage; check before buying.