Model Anatomy See what's inside open-weight AI models

Can I run gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF on an RTX 4060?

No

Even its smallest file (Q3_K_M, 6.09 GB) is more than an RTX 4060 can hold (7.20 GB usable): it needs 1 of them.

Full analysis of gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF Everything that runs on RTX 4060

Files and context on RTX 4060

Each file of gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF (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.

FileSizeOn RTX 4060 Context (16-bit)Context (8-bit)
gemma4-v2-Q8_012.7 GBDoesn't fit——
Q6_K9.79 GBDoesn't fit——
Q4_K_M7.38 GBDoesn't fit——
Q3_K_M6.09 GBDoesn't fit3K12K

gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF on other hardware

Popular models that run on RTX 4060

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.