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

Can I run Qwen3.8-27B-Uncensored-GGUF on an RTX 5090?

Yes

Its Q6_K file (22.4 GB) fits in the 28.8 GB an RTX 5090 can use, with room for ≈ 93K tokens of context.

Full analysis of Qwen3.8-27B-Uncensored-GGUF Everything that runs on RTX 5090 Get the Q6_K file on Hugging Face
ollama run hf.co/JonathanColetti/Qwen3.8-27B-Uncensored-GGUF:Q6_K

Files and context on RTX 5090

Each file of Qwen3.8-27B-Uncensored-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_029.0 GBDoesn't fit——
Qwen3.8-27B-Uncensored-noMTP-Q8_028.6 GBDoesn't fit7671K
Q6_K22.4 GBFits93K185K
Qwen3.8-27B-Uncensored-noMTP-Q6_K22.1 GBFits98K196K
Q5_K_M19.5 GBFits136K256K
Qwen3.8-27B-Uncensored-noMTP-Q5_K_M19.2 GBFits140K256K
Q4_K_M16.8 GBFits176K256K
Qwen3.8-27B-Uncensored-noMTP-Q4_K_M16.5 GBFits180K256K
IQ4_XS15.3 GBFits199K256K
Qwen3.8-27B-Uncensored-noMTP-IQ4_XS15.1 GBFits202K256K
IQ2_M10.6 GBFits256K256K
Qwen3.8-27B-Uncensored-noMTP-IQ2_M10.2 GBFits256K256K

Qwen3.8-27B-Uncensored-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.