COMPUTER RECORD · SOURCED SPECIFICATIONS

Seeed reComputer Industrial J4012: specifications and local LLMs

16 GB unified memory and 102.4 GB/s rated memory bandwidth. Fanless industrial system with Orin NX 16GB and 128GB storage.

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 · Orin NX · 8 cores / 8 threads
GPU: Ampere · 1,024 CUDA cores
Installed memory: 16 GB · LPDDR5 · 128-bit · Owner-supplied Amazon.com screenshot
Unified memory, not separate VRAM: 16 GB shared with CPU and operating system
Memory bandwidth: 102.4 GB/s rated / theoretical
Storage: 128 GB · Owner-supplied Amazon.com screenshot
Operating system: JetPack / Linux (Arm)
Expansion: Industrial I/O; M.2 storage
Edge AI advertised peak: 100 TOPS · not LLM tokens/s

The Amazon listing says the power adapter is sold separately.

Uses the original 100-TOPS industrial configuration. Seeed warns against MAXN SUPER mode on this fanless model.

Owner-supplied Amazon.com screenshot reviewed 25 Sep 2026; capture time not supplied. Industrial J4012 fanless; Orin NX 16GB selected. Storage is not shown; prior verified 128GB retained. 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 Seeed reComputer Industrial J4012 run?

The 16 GB unified-memory pool gives a 11.2 GB initial weight budget using our 30% (minimum 2 GB) reserve. The CPU, GPU and OS share this capacity; software allocation limits still apply.

84 catalog files pass this size check. The largest is Qwen3.8-27B-GSQ-RCO-GGUF at 10.094 GB (IQ3_XXS). 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
MiniCPM5 2BQ4_K_M · Pareto choice	1.561 GB	2.517B	70.8	45.346	9.639 GB	Get weights Score source
Qwen3.5-4BQ4_K_M · Pareto choice	2.741 GB	4.206B	79.1	28.859	8.459 GB	Get weights Score source
LFM2.5 230MQ4_K_M · Pareto choice	0.153 GB	0.23B	20.25	132.002	11.047 GB	Get weights Score source
Qwen3.5-9BQ4_K_M · Pareto choice	5.681 GB	9.653B	82.5	14.523	5.519 GB	Get weights Score source
gemma-4-12B-itQ4_K_M	7.122 GB	11.96B	77.2	10.84	4.078 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: B0DHXM374W · Amazon.com listing

$1,959 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: $122.438. 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

Apple Mac mini M4 Pro (2024) · 24 GB unified memory
Apple Mac mini M6 · 24GB · 24 GB unified memory
Apple Mac mini M5 Pro · 24GB · 24 GB unified memory
Apple MacBook Pro 14 M5 Pro · 24GB · 24 GB unified memory

Compare all hardware · Compare budgets