COMPUTER RECORD · SOURCED SPECIFICATIONS

NVIDIA Jetson AGX Orin 64GB Developer Kit: specifications and local LLMs

64 GB unified memory and 204.8 GB/s rated memory bandwidth. 64GB shared by CPU and CUDA GPU for embedded AI development.

Catalog reviewed 2026-10-08. Listing evidence: 2026-09-25. Price and performance records retain their own dates.

As an Amazon Associate I earn from qualifying purchases.

CPU, GPU, memory and storage

CPU: Arm Cortex-A78AE · AGX Orin · 12 cores / 12 threads
GPU: Ampere · 2,048 CUDA cores
Installed memory: 64 GB · LPDDR5 · 256-bit · Owner-supplied Amazon.com screenshot
Unified memory, not separate VRAM: 64 GB shared with CPU and operating system
Memory bandwidth: 204.8 GB/s rated / theoretical
Storage: 64 GB · Owner-supplied Amazon.com screenshot
Operating system: Ubuntu / JetPack / Linux (Arm); Docker preinstalled (screenshot)
Expansion: NVMe supported; fixed memory
Edge AI advertised peak: 275 TOPS · not LLM tokens/s

Arm / JetPack setup is required. Add NVMe for a larger model library.

The 64GB storage is onboard eMMC, not an NVMe SSD. NVIDIA specifies LPDDR5; conflicting Amazon RAM-type fields are not used.

Owner-supplied Amazon.com screenshot reviewed 25 Sep 2026; capture time not supplied. AGX Orin 64GB Developer Kit; 64GB unified memory; 275 TOPS; Ubuntu and Docker preinstalled; Ethernet, USB, DisplayPort. ASIN not visible; matched to the stored record by product name and visible configuration. No live Amazon access. Current seller, stock and checkout price can change.

What local models could NVIDIA Jetson AGX Orin 64GB Developer Kit run?

The 64 GB unified-memory pool gives a 44.8 GB initial weight budget using our 30% (minimum 2 GB) reserve. The CPU, GPU and OS share this capacity; software allocation limits still apply.

127 catalog files pass this size check. The largest is Midnight-Miqu-70B-v1.5 at 41.423 GB (Q4_K_M). This is a catalog weight limit, not a measured maximum practical model size. Context length, runtime and architecture support can rule out a candidate.

Model snapshot: 14 October 2026. The examples below use MMLU-Pro; models without that score are not ranked in this table.

MMLU-Pro memory candidates · GB = 1 billion bytes. Published scores may use different settings or precision.
Model / quantization	Weights	Parameters	Score / 100	Score / GB	Budget left	Sources
Qwen3.5-4BQ4_K_M · Pareto choice	2.741 GB	4.206B	79.1	28.859	42.059 GB	Get weights Score source
MiniCPM5 2BQ4_K_M · Pareto choice	1.561 GB	2.517B	70.8	45.346	43.239 GB	Get weights Score source
Qwen3.5-9BQ4_K_M · Pareto choice	5.681 GB	9.653B	82.5	14.523	39.119 GB	Get weights Score source
LFM2.5 230MQ4_K_M · Pareto choice	0.153 GB	0.23B	20.25	132.002	44.647 GB	Get weights Score source
Qwen3.5-27BQ4_K_M · Pareto choice	16.741 GB	27.781B	86.1	5.143	28.059 GB	Get weights Score source

Choose this computer in the memory tool · Compare its memory tier

Published LLM performance

Local AI Stats has not tested this computer. No matching token-speed result is recorded for this configuration.

Advertised compute peaks and bandwidth are not tokens per second. Compare the same model, quantization, context and concurrency.

Price and value

ASIN: B0BYGB3WV4 · Amazon.com listing

$3,399 USD reference. Amazon.com base price visible in an owner-supplied screenshot reviewed 25 Sep 2026; capture time not supplied. Dated reference, not a live quote. Excludes card signup offers, coupons, tax and shipping.

Reference price per installed-memory GB: $53.109. This measures cost per GB, not speed or total running cost.

As an Amazon Associate I earn from qualifying purchases. Check the exact configuration, seller, marketplace and current price before buying.

GET NOW · Amazon

Related hardware

GMKtec EVO-X2 · 64 GB unified memory
MINISFORUM N5 MAX · 64GB · 64 GB unified memory
Apple Mac Studio M5 Max · 36GB · 36 GB unified memory
Apple MacBook Pro 14 M5 Max · 36GB · 36 GB unified memory

Compare all hardware · Compare budgets