Local AI Stats.
Skip to content

COMPUTER RECORD · SOURCED SPECIFICATIONS

MINISFORUM N5 MAX · 64GB: specifications and local LLMs

64 GB unified memory and 256 GB/s rated memory bandwidth. 64GB unified memory; five SATA bays and five M.2 slots; dual 10GbE and USB4 v2.

Catalog reviewed . Listing evidence: 2026-10-01. 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 Max+ 395 · 16 cores / 32 threads
GPU
Radeon 8060S · 40 CUs
Installed memory
64 GB · LPDDR5X unified · Owner-supplied; Amazon.com not verified
Unified memory, not separate VRAM
64 GB shared with CPU and operating system
Memory bandwidth
256 GB/s rated / theoretical · Theoretical default: LPDDR5X-8000 × 256-bit / 8. The manufacturer lists 8533 MT/s only as a user-configurable overclock.
Storage
128 GB · Owner-supplied; Amazon.com not verified
Operating system
MinisCloud OS (manufacturer)
Expansion
Five 3.5/2.5-inch SATA bays; five M.2 slots including the system SSD; dual 10GbE; dual USB4 v2
NPU advertised peak
50 TOPS · not LLM tokens/s
Whole-chip advertised peak
126 TOPS · distinct from NPU-only performance

Fixed RAM; independent testing found immature MinisCloud software and a 48GB maximum GPU-memory allocation on the reviewed 64GB unit.

The Amazon and manufacturer configuration is 64GB LPDDR5X with a 128GB system SSD. Advertised 200TB capacity describes supported user-added drives, not included storage.

Selected ASIN and configuration matched the indexed Amazon.com product title on 1 October 2026. The direct Amazon page returned an access error, so this is not a live price or stock check. Manufacturer specifications and an independent review match the 64GB configuration. Current seller, stock and checkout price can change.

What local models could MINISFORUM N5 MAX · 64GB 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 / quantizationWeightsParametersScore / 100Score / GBBudget leftSources
Qwen3.5-4BQ4_K_M · Pareto choice2.741 GB4.206B79.128.85942.059 GBGet weights
Score source
MiniCPM5 2BQ4_K_M · Pareto choice1.561 GB2.517B70.845.34643.239 GBGet weights
Score source
Qwen3.5-9BQ4_K_M · Pareto choice5.681 GB9.653B82.514.52339.119 GBGet weights
Score source
LFM2.5 230MQ4_K_M · Pareto choice0.153 GB0.23B20.25132.00244.647 GBGet weights
Score source
Qwen3.5-27BQ4_K_M · Pareto choice16.741 GB27.781B86.15.14328.059 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: B0FR9FVC5L · Amazon.com listing

No matching current USD price verified. No verified Amazon.com price for this exact configuration. 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

Compare all hardware · Compare budgets

Specification and price sources