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

Can I run Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF on an RTX 3060 12 GB?

Yes, just

Its Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-Q8_0 file (10.5 GB) fits in the 10.8 GB an RTX 3060 12 GB can use, with room for ≈ 8K tokens of context.

Full analysis of Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF Everything that runs on RTX 3060 12 GB Get the Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-Q8_0 file on Hugging Face
ollama run hf.co/DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF

Files and context on RTX 3060 12 GB

Each file of Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-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)
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-plusIQ-TOOLS-NEO-MAX-MTP-Q8_010.7 GBDoesn't fit270540
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-plusIQ-NEO-MAX-MTP-Q8_010.7 GBDoesn't fit270541
Q8_010.7 GBDoesn't fit270541
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-Q8_010.5 GBTight8K16K
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-plusIQ-TOOLS-NEO-MAX-MTP-Q6_K8.76 GBTight59K119K
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-plusIQ-NEO-MAX-MTP-Q6_K8.76 GBTight59K119K
Q6_K8.76 GBTight59K119K
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-Q6_K8.56 GBFits65K130K
Q5_K_M7.84 GBFits87K173K
Q5_K_S7.67 GBFits92K183K
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-Q5_K_M7.67 GBFits92K184K
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-Q5_K_S7.51 GBFits97K193K
Q4_K_M6.98 GBFits112K225K
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-Q4_K_M6.83 GBFits117K234K
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-MTP-IQ4_NL6.76 GBFits119K238K
Q4_K_S6.69 GBFits121K242K
IQ4_NL6.62 GBFits123K246K
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-Q4_K_S6.55 GBFits125K250K
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-MTP-IQ4_XS6.53 GBFits126K252K
IQ4_XS6.40 GBFits130K256K
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-MTP-IQ3_M5.72 GBFits150K256K
IQ3_M5.62 GBFits153K256K
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-MTP-IQ2_M4.94 GBFits173K256K
IQ2_M4.94 GBFits173K256K

Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-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.