Can I run Victoria on an RTX 3060 12 GB?

Even its smallest file (victoria-s410-bitexact-tbl8, 107 GB) is more than an RTX 3060 12 GB can hold (10.8 GB usable): it needs more than 8 of them.

Full analysis of Victoria Everything that runs on RTX 3060 12 GB

Files and context on RTX 3060 12 GB

Each file of Victoria (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.

File	Size	On RTX 3060 12 GB	Context (16-bit)	Context (8-bit)
victoria-s410-bitexact	155 GB	Doesn't fit	—	—
victoria-s410-bitexact-tbl8	107 GB	Doesn't fit	—	—

Victoria on other hardware

NVIDIA H100No
RTX 5090No
RTX 4090No
RTX 3090No
RTX 5060 Ti 16 GBNo
RTX 3060 12 GBNo
RTX 4060No
Mac with 32 GBNo
Mac with 64 GBNo
Mac with 128 GBNo

Popular models that run on RTX 3060 12 GB

Qwen3-0.6BQwen · 752M
gpt2openai-community · 137M
Qwen3-Coder-30B-A3B-Instruct-GGUFunsloth · 30.5B
Qwen2.5-0.5B-InstructQwen · 494M
Qwen2.5-1.5B-InstructQwen · 1.54B
Qwen3-4BQwen · 4.02B
Qwen3.5-4BQwen · 4.66B
Ornith-1.5-9B-GGUFornith-ai · 9.20B

Assumes 90% of the card's memory is usable and at least 4K tokens of context for one conversation, with the context cache in 16-bit unless noted. Fits leaves at least 20% of that memory for context; Tight leaves less.