Any 12gb VRAM users out there?
A user with a 3080 12GB VRAM graphics card is seeking advice on optimal models to utilize the extra 4GB of VRAM compared to 8GB cards, while remaining within a 16GB VRAM limit. They note that Qwen 3.6 35B 3A was previously a popular choice but are interested in other specifically optimized models that could meaningfully benefit from their card's capacity.
Why this oneThis post specifically addresses the challenge of optimizing AI models for 12GB VRAM cards, unlike general discussions that often focus on 8GB or 16GB configurations.
Time & source
Times shown in UTC
Display time zone: UTC
Local time zone unavailable; showing UTC.
PublishedOffset at this time: UTC+0Sep 11, 2026, 16:32 UTC
IngestedOffset at this time: UTC+0Sep 12, 2026, 15:01 UTC
- Published
- Sep 11, 2026, 16:32
- Ingested
- Sep 12, 2026, 15:01
- Source type
- Dev community
- Tier
- Community
- Source status
- Healthy
Tier is a per-source editorial setting, not a per-item score.
Discussion trend
The percentage is based on collected discussion signal, not new comments or independent people. The curve only compares the same topic across time.
Hi!
I've been following this community for quite a while and have difficulty figuring out what to put on my 3080 12gb - I know Qwen 3.6 35B 3A was the go-to choice when it first came out, but I'm curious if there are any other models / specifically optimized models that meaningfully benefit from the extra 4gb of VRAM over 8gb while still being usable under 16gb.
My workflow is agent heavy, but more for a personal secretary and manager, and less coding heavy.