cd /news/artificial-intelligence/vram-and-multi-gpu-setups · home topics artificial-intelligence article
[ARTICLE · art-119572] src=forum.level1techs.com ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

VRAM and multi-GPU setups

A forum user on Level1Techs asks whether two AMD Radeon RX 9070 XT-class 32GB GPUs (R9700) can run a large language model locally with 64GB VRAM, noting that models must fit on one GPU or be split across cards. The user plans to use the setup for local AI inference to avoid API fees, with a Threadripper server supporting up to four cards for 128GB VRAM.

read1 min views1 publishedSep 2, 2026
VRAM and multi-GPU setups
Image: Forum (auto-discovered)

JBinFla 1 So I’m late to the party guys. A couple months back finally started paying for Codex and wow. But. I don’t want to get API fees so I’d like to stay local. I need a GPU as I don’t wanna use my laptop 5080 and my server is an RX5700 I use for Plex transcoding. I’m looking at the Strix Halo stuff but am wondering if I get two AMD R9700 32gb cards (card vs card roughly equivalent perf to 9070 XT). This is way faster and will have 64gb VRAM for about $3k, and since my server is a threadripper (I know) I have enough slots and lanes to go to 4 cards at 128gb should the need arise.

Question: Can I use 2x 32gb cards roughly equivalent to one 64gb card just twice as fast or does the model have to fit on one GPU?

You can get two cards and run them once as fast. This is still pretty great.

the idea would be to up the vram total to be able to load a larger model / larger context / overall less quantized llm - at speed. with 2x r9700 you will be having a good time with Qwen3.8-27B. 4x r9700 then Qwen3.8-Flash-Next, Deepseek v4 Flash 0731 / GLM 5.3 flash (with some ram overflow) is probably where you will be aiming at - depending on use case (eg how many users need access to the ai?)

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @level1techs 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/vram-and-multi-gpu-s…] indexed:0 read:1min 2026-09-02 ·