Can I run Mellum2.1-12B-A2.5B-Thinking on an RTX 4090?

Yes, with a GGUF version

The published weights are too big, but the Mellum2.1-12B-A2.5B-Thinking-MTP-Q8_0 file from JetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF (13.4 GB) fits, with room for ≈ 128K tokens of context.

Full analysis of Mellum2.1-12B-A2.5B-Thinking Everything that runs on RTX 4090 Get the Mellum2.1-12B-A2.5B-Thinking-MTP-Q8_0 file on Hugging Face

ollama run hf.co/JetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF

Files and context on RTX 4090

Each file of Mellum2.1-12B-A2.5B-Thinking (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.

File	Size	On RTX 4090	Context (16-bit)	Context (8-bit)
As published	24.3 GB	Doesn't fit	—	—
Mellum2.1-12B-A2.5B-Thinking-MTP-BF16JetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF	25.2 GB	Doesn't fit	—	—
BF16JetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF	24.3 GB	Doesn't fit	—	—
Mellum2.1-12B-A2.5B-Thinking-MTP-Q8_0JetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF	13.4 GB	Fits	128K	128K
Q8_0JetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF	12.9 GB	Fits	128K	128K
Mellum2.1-12B-A2.5B-Thinking-MTP-Q6_KJetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF	11.3 GB	Fits	128K	128K
Q6_KJetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF	10.9 GB	Fits	128K	128K
Mellum2.1-12B-A2.5B-Thinking-MTP-Q4_K_MJetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF	8.33 GB	Fits	128K	128K
Q4_K_MJetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF	8.07 GB	Fits	128K	128K
Mellum2.1-12B-A2.5B-Thinking-MTP-MXFP4_MOEJetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF	7.27 GB	Fits	128K	128K
MXFP4_MOEJetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF	7.03 GB	Fits	128K	128K

Mellum2.1-12B-A2.5B-Thinking on other hardware

Popular models that run on RTX 4090

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.