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

Can I run Qwythos-9B-Claude-Mythos-5-1M-GGUF on an RTX 3090?

Yes, just

Its Qwythos-9B-Claude-Mythos-5-1M-MTP-BF16 file (18.4 GB) fits in the 21.6 GB an RTX 3090 can use, with room for ≈ 94K tokens of context.

Full analysis of Qwythos-9B-Claude-Mythos-5-1M-GGUF Everything that runs on RTX 3090 Get the Qwythos-9B-Claude-Mythos-5-1M-MTP-BF16 file on Hugging Face
ollama run hf.co/empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF

Files and context on RTX 3090

Each file of Qwythos-9B-Claude-Mythos-5-1M-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)
Qwythos-9B-Claude-Mythos-5-1M-MTP-BF1618.4 GBTight94K187K
BF1617.9 GBTight108K216K
Q8_09.79 GBFits351K701K
Qwythos-9B-Claude-Mythos-5-1M-Q8_09.53 GBFits358K717K
Q6_K7.62 GBFits415K830K
Qwythos-9B-Claude-Mythos-5-1M-Q6_K7.36 GBFits423K846K
Q5_K_M6.73 GBFits442K883K
Qwythos-9B-Claude-Mythos-5-1M-Q5_K_M6.47 GBFits449K899K
Q4_K_M5.89 GBFits467K933K
Qwythos-9B-Claude-Mythos-5-1M-Q4_K_M5.63 GBFits474K949K

Qwythos-9B-Claude-Mythos-5-1M-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.