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

Can I run Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF on an RTX 3060 12 GB?

No

Even its smallest file (IQ2_M, 11.7 GB) is more than an RTX 3060 12 GB can hold (10.8 GB usable): it needs 2 of them.

Full analysis of Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF Everything that runs on RTX 3060 12 GB

Files and context on RTX 3060 12 GB

Each file of Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-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 3060 12 GB Context (16-bit)Context (8-bit)
Q8_030.2 GBDoesn't fit——
Qwen3.6-27B-Fable-Fus-711-UnHeretic-NM-DAU-NEO-MAX-NEO-Q8_029.8 GBDoesn't fit——
Q6_K24.0 GBDoesn't fit——
Qwen3.6-27B-Fable-Fus-711-UnHeretic-NM-DAU-NEO-MAX-NEO-MTP-Q6_K24.0 GBDoesn't fit——
Qwen3.6-27B-Fable-Fus-711-UnHeretic-NM-DAU-NEO-MAX-NEO-Q6_K23.6 GBDoesn't fit——
Qwen3.6-27B-Fable-Fus-711-UnHeretic-NM-DAU-NEO-MAX-NEO-LOW-MTP-Q6_K22.8 GBDoesn't fit——
Q5_K_M21.2 GBDoesn't fit——
Qwen3.6-27B-Fable-Fus-711-UnHeretic-NM-DAU-NEO-MAX-NEO-Q5_K_M20.7 GBDoesn't fit——
Q5_K_S20.6 GBDoesn't fit——
Qwen3.6-27B-Fable-Fus-711-UnHeretic-NM-DAU-NEO-MAX-NEO-Q5_K_S20.2 GBDoesn't fit——
Q4_K_M18.5 GBDoesn't fit——
Qwen3.6-27B-Fable-Fus-711-UnHeretic-NM-DAU-NEO-MAX-NEO-Q4_K_M18.0 GBDoesn't fit——
Qwen3.6-27B-Fable-Fus-711-UnHeretic-NM-DAU-NEO-MAX-NEO-MTP-IQ4_NL17.8 GBDoesn't fit——
Q4_K_S17.5 GBDoesn't fit——
IQ4_NL17.3 GBDoesn't fit——
Qwen3.6-27B-Fable-Fus-711-UnHeretic-NM-DAU-NEO-MAX-NEO-Q4_K_S17.1 GBDoesn't fit——
Qwen3.6-27B-Fable-Fus-711-UnHeretic-NM-DAU-NEO-MAX-NEO-MTP-IQ4_XS17.0 GBDoesn't fit——
IQ4_XS16.8 GBDoesn't fit——
Qwen3.6-27B-Fable-Fus-711-UnHeretic-NM-DAU-NEO-MAX-NEO-IQ4_XS16.6 GBDoesn't fit——
Qwen3.6-27B-Fable-Fus-711-UnHeretic-NM-DAU-NEO-MAX-NEO-LOW-MTP-IQ4_XS15.1 GBDoesn't fit——
Qwen3.6-27B-Fable-Fus-711-UnHeretic-NM-DAU-NEO-MAX-NEO-MTP-IQ3_M14.5 GBDoesn't fit——
IQ3_M14.1 GBDoesn't fit——
Qwen3.6-27B-Fable-Fus-711-UnHeretic-NM-DAU-NEO-MAX-NEO-MTP-IQ2_M12.1 GBDoesn't fit——
IQ2_M11.7 GBDoesn't fit——

Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF on other hardware

Popular models that run on RTX 3060 12 GB

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.