Can I run Spark-X2.6-4B-abliterated-FIT-GGUF on an RTX 3090?

Yes

Its BF16 file (8.23 GB) fits in the 21.6 GB an RTX 3090 can use, with room for ≈ 353K tokens of context.

Full analysis of Spark-X2.6-4B-abliterated-FIT-GGUF Everything that runs on RTX 3090 Get the BF16 file on Hugging Face

ollama run hf.co/SC117/Spark-X2.6-4B-abliterated-FIT-GGUF:BF16

Files and context on RTX 3090

Each file of Spark-X2.6-4B-abliterated-FIT-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)
BF16	8.23 GB	Fits	353K	707K
Q6_K	3.38 GB	Fits	481K	964K
Q5_K_M	3.00 GB	Fits	491K	984K
Q4_K_M	2.70 GB	Fits	499K	1000K
IQ4_XS	2.38 GB	Fits	508K	1017K
Q3_K_M	2.34 GB	Fits	509K	1019K

Spark-X2.6-4B-abliterated-FIT-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.