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

Can I run Cyber-Tiel-Coder-35B-A3B-GGUF-MTP on an RTX 5080?

Yes, just

Its UD-IQ3_XXS file (13.6 GB) fits in the 14.4 GB an RTX 5080 can use, with room for ≈ 35K tokens of context.

Full analysis of Cyber-Tiel-Coder-35B-A3B-GGUF-MTP Everything that runs on RTX 5080 Get the UD-IQ3_XXS file on Hugging Face
ollama run hf.co/peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP:UD-IQ3_XXS

Files and context on RTX 5080

Each file of Cyber-Tiel-Coder-35B-A3B-GGUF-MTP (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 5080 Context (16-bit)Context (8-bit)
UD-Q8_K_XL38.8 GBDoesn't fit——
UD-Q6_K_XL32.2 GBDoesn't fit——
UD-Q5_K_XL27.0 GBDoesn't fit——
UD-Q4_K_XL22.7 GBDoesn't fit——
UD-Q4_K_M22.5 GBDoesn't fit——
UD-Q4_K_S21.3 GBDoesn't fit——
UD-IQ4_XS18.1 GBDoesn't fit——
UD-Q3_K_XL17.2 GBDoesn't fit——
UD-IQ3_XXS13.6 GBTight35K70K
UD-Q2_K_XL12.7 GBTight79K158K

Cyber-Tiel-Coder-35B-A3B-GGUF-MTP on other hardware

Popular models that run on RTX 5080

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.