Can I run Hy-Memory-30B-A3B-GGUF on an RTX 3090?

Yes, just

Its Q4_K_M file (18.2 GB) fits in the 21.6 GB an RTX 3090 can use, with room for ≈ 33K tokens of context.

Full analysis of Hy-Memory-30B-A3B-GGUF Everything that runs on RTX 3090 Get the Q4_K_M file on Hugging Face

ollama run hf.co/tencent/Hy-Memory-30B-A3B-GGUF:Q4_K_M

Files and context on RTX 3090

Each file of Hy-Memory-30B-A3B-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.

File	Size	On RTX 3090	Context (16-bit)	Context (8-bit)
Hy-Memory-30B-A3B-Q8_0	32.0 GB	Doesn't fit	—	—
Q6_K	24.7 GB	Doesn't fit	—	—
Q4_K_M	18.2 GB	Tight	33K	67K
Q3_K_M	14.4 GB	Fits	71K	142K
Hy-Memory-30B-A3B-Q8_0-expsIQ2_XXS	9.14 GB	Fits	124K	247K
Q8_0	8.03 GB	Fits	135K	256K

Hy-Memory-30B-A3B-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.