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

Can I run Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF on an RTX 5090?

Yes, just

Its Qwen3.8-27B-TurboFCFusion-735-882-Here-Uncen-NEO-CODER-MAX-MTP-Q6_K file (24.0 GB) fits in the 28.8 GB an RTX 5090 can use, with room for ≈ 69K tokens of context.

Full analysis of Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF Everything that runs on RTX 5090 Get the Qwen3.8-27B-TurboFCFusion-735-882-Here-Uncen-NEO-CODER-MAX-MTP-Q6_K file on Hugging Face
ollama run hf.co/DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF

Files and context on RTX 5090

Each file of Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-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 5090 Context (16-bit)Context (8-bit)
Q8_030.2 GBDoesn't fit——
Qwen3.8-27B-TurboFCFusion-735-882-Here-Uncen-NEO-CODER-MAX-Q8_029.8 GBDoesn't fit——
Qwen3.8-27B-TurboFCFusion-735-882-Here-Uncen-NEO-CODER-MAX-MTP-Q6_K24.0 GBTight69K137K
Qwen3.8-27B-TurboFCFusion-735-882-Here-Uncen-NEO-CODER-MAX-Q6_K23.6 GBTight75K151K
Q6_K22.4 GBFits93K185K
Q5_K_M21.2 GBFits111K222K
Qwen3.8-27B-TurboFCFusion-735-882-Here-Uncen-NEO-CODER-MAX-Q5_K_M20.7 GBFits118K236K
Q5_K_S20.6 GBFits119K239K
Qwen3.8-27B-TurboFCFusion-735-882-Here-Uncen-NEO-CODER-MAX-Q5_K_S20.2 GBFits126K252K
Q4_K_M18.5 GBFits151K256K
Qwen3.8-27B-TurboFCFusion-735-882-Here-Uncen-NEO-CODER-MAX-Q4_K_M18.0 GBFits158K256K
Q4_K_S17.5 GBFits166K256K
Qwen3.8-27B-TurboFCFusion-735-882-Here-Uncen-NEO-CODER-MAX-Q4_K_S17.1 GBFits172K256K
Qwen3.8-27B-TurboFCFusion-735-882-Here-Uncen-NEO-CODER-MAX-MTP-IQ4_XS17.0 GBFits173K256K
IQ4_XS16.6 GBFits180K256K
Qwen3.8-27B-TurboFCFusion-735-882-Here-Uncen-NEO-CODER-MAX-LOW-MTP-IQ4_XS15.3 GBFits199K256K
Qwen3.8-27B-TurboFCFusion-735-882-Here-Uncen-NEO-CODER-MAX-MTP-IQ3_M14.5 GBFits210K256K
IQ3_M14.1 GBFits217K256K
Qwen3.8-27B-TurboFCFusion-735-882-Here-Uncen-NEO-CODER-MAX-MTP-IQ2_M12.1 GBFits246K256K
IQ2_M11.7 GBFits253K256K

Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF on other hardware

Popular models that run on RTX 5090

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.