ITItaliano
Accedi
Menu

Migliore Server chat LLM locale

Un server domestico per chat LLM privata (Ollama + Open WebUI), completamento codice locale e fine-tuning LoRA — tanta VRAM, tanta RAM.

La richiesta
  • Inferenza AI locale
  • Assistente codice (LLM locale)
  • Addestramento modelli
Modifica richiesta
Panoramica · Unified-memory build€3,247

Requisiti vs questa build

necessario · usato
Thread CPU1856%OK
RAM96 GB75%OK
Archiviazione4 TB99%Pieno
GPUAdatta all'IA

Consumi

Utilizzo
24/7
A riposo
13 W
Tipico
14 W
Picco
38 W
Energia / anno
≈ €31
In 3 anni
≈ €92

Punteggio

Complessivo69
Prestazioni76
Efficienza93
Valore51

Perché questa variante

Sceglila se

Balances your priorities with a 3247€ price tag and a 13W idle draw.

Cosa sacrifica
  • Not specialized: it does not push any single dimension (value, silence, expansion) to the extreme.
Come sono stati scelti i componenti
  • GMKtec EVO-X2 — AMD Ryzen AI Max+ 395: 32 threads, 128GB RAM, 12W idle — a complete, efficient prebuilt for this workload.
  • Turnkey: no assembly, smaller footprint, lower energy than a custom build.
  • Unified memory: the integrated GPU can use up to ~96 GB of the 128 GB as graphics memory, so the model fits without a dedicated card. Decode speed follows the 256 GB/s memory bus — several times slower than a high-end card, but a fraction of its price and power.
Perché non le altre
  • Unified-memory build — the model in shared RAM, no card beats "Smart build — best all-round" on performance -24, value +51, efficiency +93, expandability -52, longevity +16 — that is why it is recommended for your priorities.
  • Unified-memory build — the model in shared RAM, no card beats "Long-term build — expandable & future-proof" on performance -24, value +51, efficiency +93, expandability -61, longevity +7 — that is why it is recommended for your priorities.

Prima di acquistare

2 critici
Critico
Check the balance
This build may struggle with the workload.
Critico
No storage redundancy
1 drive(s) with no mirror or parity for the data you plan to store.