PC Build to Run Qwen 3.6 35B-A3B Locally (Q8_0)

Name: LLM Configurator — GPU VRAM Checker
Author: LLM Configurator

Written by Jakub Rusinowski · Last updated July 10, 2026

A complete parts list — GPU, motherboard, RAM and PSU — worked backward from Qwen 3.6 35B-A3B's VRAM requirement at Q8_0. Prices are 2026 street estimates and vary.

Requirements

VRAM required	~38 GB at Q8_0
System RAM	32 GB
Complete build (est.)	$3,303

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.

GPU: 2× AMD Radeon RX 7900 XT

2× AMD Radeon RX 7900 XT (40 GB pooled) covers Qwen 3.6 35B-A3B at Q8_0 (~38 GB needed), a tight fit — little headroom.

Check price on Amazon — AMD Radeon RX 7900 XT 20GB

Motherboard: ASUS ProArt X670E-Creator WIFI

X670E (AM5) — pairs with the AMD Ryzen 9 7900X; DDR5, dual PCIe 5.0 x16 (x8/x8) for multi-GPU, 4 DIMM slots to 192 GB.

Check price on Amazon — ASUS ProArt X670E-Creator WIFI

RAM: Corsair Vengeance 32GB (2x16GB) DDR5-6000 C30 (AMD EXPO)

32 GB DDR5-6000 (2x16GB) meets Qwen 3.6 35B-A3B's 32 GB recommended system RAM.

Check price on Amazon — Corsair Vengeance 32GB (2x16GB) DDR5-6000 C30

PSU: Corsair HX1500i (ATX 3.1)

1500 W 80+ Platinum covers 2× AMD Radeon RX 7900 XT (630 W) + CPU 170 W with 30% headroom (~1040 W required).

Check price on Amazon — Corsair HX1500i (ATX 3.1)

Swap Alternatives

GPU: NVIDIA RTX 6000 Ada Generation — Single-GPU alternative (no tensor split, simpler): NVIDIA RTX 6000 Ada Generation 48 GB at $6,799.
RAM: Corsair Vengeance 64GB (2x32GB) DDR5-6000 C30 (AMD EXPO) — More headroom: 64 GB DDR5-6000.

Qwen 3.6 35B-A3B at Q8_0 needs more VRAM than any single consumer GPU, so this uses 2× AMD Radeon RX 7900 XT (40 GB pooled via tensor split) — cheaper than the single NVIDIA RTX 6000 Ada Generation (48 GB, $6,799) that would also fit.
The AMD Radeon RX 7900 XT is a tight fit at Q8_0 — consider an upgrade alternative for KV-cache/context headroom.

FAQ

What GPU do I need to run Qwen 3.6 35B-A3B at Q8_0?

2× AMD Radeon RX 7900 XT (40 GB pooled) covers Qwen 3.6 35B-A3B at Q8_0 (~38 GB needed), a tight fit — little headroom.

How much VRAM does Qwen 3.6 35B-A3B need at Q8_0?

About 38 GB of VRAM plus 32 GB of system RAM.

What power supply does a AMD Radeon RX 7900 XT build need?

1500 W 80+ Platinum covers 2× AMD Radeon RX 7900 XT (630 W) + CPU 170 W with 30% headroom (~1040 W required).

How much does a Qwen 3.6 35B-A3B PC cost?

About $3,303 for a complete build (GPU, motherboard, RAM, PSU, CPU, case, SSD), at 2026 street-price estimates.

Qwen 3.6 35B-A3B at Other Quant Levels

Other Popular Build Targets

Model & GPU

More Ways to Build

← Budget-first build recommender | Qwen 3.6 model page | AMD Radeon RX 7900 XT review