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

Can I run LFM2.5-24B-A2B-GGUF on an RTX 3090?

Yes, just

Its UD-Q5_K_XL file (17.9 GB) fits in the 21.6 GB an RTX 3090 can use, with room for ≈ 128K tokens of context.

Full analysis of LFM2.5-24B-A2B-GGUF Everything that runs on RTX 3090 Get the UD-Q5_K_XL file on Hugging Face
ollama run hf.co/unsloth/LFM2.5-24B-A2B-GGUF:UD-Q5_K_XL

Files and context on RTX 3090

Each file of LFM2.5-24B-A2B-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 3090 Context (16-bit)Context (8-bit)
BF1648.0 GBDoesn't fit——
Q8_025.5 GBDoesn't fit——
UD-Q6_K_XL21.9 GBDoesn't fit——
UD-Q5_K_XL17.9 GBTight128K128K
UD-Q4_K_XL14.9 GBFits128K128K
UD-Q3_K_XL10.9 GBFits128K128K
UD-IQ3_XXS8.96 GBFits128K128K
UD-Q2_K_XL8.04 GBFits128K128K
UD-IQ2_M7.54 GBFits128K128K
UD-IQ2_XXS7.47 GBFits128K128K

LFM2.5-24B-A2B-GGUF on other hardware

Popular models that run on RTX 3090

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.