COMPUTER RECORD · SOURCED SPECIFICATIONS

MINISFORUM AI X1 Pro · 96GB: specifications and local LLMs

96 GB system RAM. 96GB installed RAM; replaceable SO-DIMMs; OCuLink for external GPU expansion.

Catalog reviewed 2026-10-08. Listing evidence: 2026-09-30. Price and performance records retain their own dates.

As an Amazon Associate I earn from qualifying purchases.

CPU, GPU, memory and storage

CPU: Ryzen AI 9 HX 370 · 12 cores / 24 threads
GPU: Radeon 890M · 16 CUs
Installed memory: 96 GB · DDR5 · Amazon.com ASIN listing
GPU memory pool: Shared allocation not verified
Memory bandwidth: Not verified for this installed configuration
Storage: 2000 GB · Amazon.com ASIN listing
Operating system: Not verified
Expansion: Two SO-DIMMs; three M.2 slots; OCuLink PCIe 4.0 x4; dual USB4; dual 2.5GbE
NPU advertised peak: 50 TOPS · not LLM tokens/s
Whole-chip advertised peak: 80 TOPS · distinct from NPU-only performance

Shared system memory; large-model inference speed depends on runtime and GPU offload.

HX 370 configuration, not the newer HX 470 model. Installed memory bandwidth and usable GPU allocation have not been measured.

Selected ASIN and configuration matched the indexed Amazon.com product title on 30 September 2026. The retrieved page omitted the main offer price; this is not a live price or stock check. Current seller, stock and checkout price can change.

What local models could MINISFORUM AI X1 Pro · 96GB run?

The 96 GB system-RAM pool gives a 67.2 GB initial weight budget using our 30% (minimum 2 GB) reserve. This is a CPU-inference budget. Integrated-GPU allocation is not established.

128 catalog files pass this size check. The largest is Aleph Alpha Kolibri-1 at 47.454 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	64.459 GB	Get weights Score source
MiniCPM5 2BQ4_K_M · Pareto choice	1.561 GB	2.517B	70.8	45.346	65.639 GB	Get weights Score source
Qwen3.5-9BQ4_K_M · Pareto choice	5.681 GB	9.653B	82.5	14.523	61.519 GB	Get weights Score source
LFM2.5 230MQ4_K_M · Pareto choice	0.153 GB	0.23B	20.25	132.002	67.047 GB	Get weights Score source
Qwen3.5-27BQ4_K_M · Pareto choice	16.741 GB	27.781B	86.1	5.143	50.459 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: B0F47FD6DY · Amazon.com listing

No matching current USD price verified. No verified USD price for this exact configuration. Amazon price and stock are unconfirmed.

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-T1 · 64 GB system RAM
msecore Ryzen AI 9 HX 370 Workstation · 64 GB system RAM
GMKtec EVO-T2S · 64GB · 64 GB system RAM
Reatan X8 · 48 GB system RAM

Compare all hardware · Compare budgets