Local AI Stats.
Skip to content

COMPUTER RECORD · SOURCED SPECIFICATIONS

GMKtec K15 · 16GB: specifications and local LLMs

16 GB system RAM. 16GB RAM and a 512GB SSD with external GPU and storage expansion.

Catalog reviewed . Listing evidence: 2026-09-24. Price and performance records retain their own dates.

As an Amazon Associate I earn from qualifying purchases.

CPU, GPU, memory and storage

CPU
Core Ultra 5 125U · 12 cores / 14 threads
GPU
Intel Graphics
Installed memory
16 GB · DDR5 · speed unverified · Owner-supplied Amazon.com screenshot
GPU memory pool
Shared allocation not verified
Memory bandwidth
Not verified for this installed configuration
Storage
512 GB · Owner-supplied Amazon.com screenshot
Operating system
Windows 11 Pro (manufacturer specification)
Expansion
Three M.2 2280 slots; OCuLink; USB4; dual 2.5GbE
NPU advertised peak
11 TOPS · not LLM tokens/s
Whole-chip advertised peak
21 TOPS · distinct from NPU-only performance

Low-power CPU and shared graphics limit large-model inference.

The screenshot confirms 125U / 16GB / 512GB. Its 12T / 14C title reverses the counts: the 125U has 12 cores and 14 threads. Installed module count and speed are not shown; bandwidth remains unverified. Windows 11 Pro is the manufacturer specification; the Amazon seller license was not independently checked.

Owner-supplied Amazon.com screenshot reviewed 24 Sep 2026 and matched by the owner to ASIN B0H7JFVGFK. The screenshot shows the product title and price, but not the ASIN or capture time. It is not an independent live listing check. Current seller, stock and checkout price can change.

What local models could GMKtec K15 · 16GB run?

The 16 GB system-RAM pool gives a 11.2 GB initial weight budget using our 30% (minimum 2 GB) reserve. This is a CPU-inference budget. Integrated-GPU allocation is not established.

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 / quantizationWeightsParametersScore / 100Score / GBBudget leftSources
MiniCPM5 2BQ4_K_M · Pareto choice1.561 GB2.517B70.845.3469.639 GBGet weights
Score source
Qwen3.5-4BQ4_K_M · Pareto choice2.741 GB4.206B79.128.8598.459 GBGet weights
Score source
LFM2.5 230MQ4_K_M · Pareto choice0.153 GB0.23B20.25132.00211.047 GBGet weights
Score source
Qwen3.5-9BQ4_K_M · Pareto choice5.681 GB9.653B82.514.5235.519 GBGet weights
Score source
gemma-4-12B-itQ4_K_M7.122 GB11.96B77.210.844.078 GBGet 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: B0H7JFVGFK · Amazon.com listing

$559.98 USD reference. Amazon.com price shown in an owner-supplied screenshot reviewed 24 Sep 2026; capture time not provided. Excludes shipping, import charges, tax and optional discounts. This is a dated reference, not a live checkout quote. The screenshot shows a limited-time deal; its end date is not visible.

Reference price per installed-memory GB: $34.999. 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

Compare all hardware · Compare budgets

Specification and price sources