Community in 5 languagesGlobal + local opinion
Trending in United StatesGlobal Top 100What the World SaysCategoriesCountriesHow We Rank
TRENDEESPT
Local AI

Which graphics cards run Qwen3.5 9B?

Whether a model runs on your machine is decided first by the graphics card's memory: the model file has to fit in VRAM with room left for the context window and the runtime. The states below are computed from memory alone; software support (CUDA, ROCm, Vulkan) is a separate matter.

6.6 GBVRAM
45Comfortable
35Runs
Local AI

State by VRAM

Ollama default package 6.6 GB

VRAMLocal AIBy VRAM
32 GBComfortable1 card
24 GBComfortable5 cards
20 GBComfortable1 card
16 GBComfortable20 cards
12 GBComfortable15 cards
11 GBComfortable1 card
10 GBComfortable2 cards
8 GBRuns35 cards
6 GBLimited8 cards
4 GBLimited11 cards

Rule: 1.5× the requirement in memory is Comfortable, 1.15× Runs, 0.6× Limited; the requirement is the default package size, or the maker's stated minimum where there is one (a stated minimum counts as fitting at exactly that figure). Package sizes are the Ollama library's, minimums the maker's own statement; read on 2026-09-11. Sources: ollama.com/library/qwen3.5

Comfortable

Cards that run it comfortably

Runs

Cards that fit it

Limited

Cards that run it limited

Local AI

Other models