Is L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B or llama-3-youko-8b smaller?

Both publish quantizations; compare the table for the exact sizes.

Which uses less memory at long context?

llama-3-youko-8b — its KV cache at 32K context is 2.1x smaller, because of how its attention layers cache.

Model comparison

L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B vs llama-3-youko-8b

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: llama-3-youko-8b's KV cache at 32K is 2.1× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B	llama-3-youko-8b
Parameters	7.5B	8.0B
Architecture	llama	llama
Layers	67	32
Native context	131,072	8,192
Mixture of experts	no	no
Quantizations published	10	2
Smallest quantization	2.73 GiB	5.34 GiB
Q4_K_M	4.27 GiB	—
Licence	apache-2.0	llama3

KV cache by context

the term that decides long-context viability

Context	L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B	llama-3-youko-8b	Ratio
4,096	1.05 GiB	0.50 GiB	2.09×
8,192	2.09 GiB	1.00 GiB	2.09×
16,384	4.19 GiB	2.00 GiB	2.09×
32,768	8.38 GiB	4.00 GiB	2.09×
65,536	16.75 GiB	8.00 GiB	2.09×
131,072	33.50 GiB	16.00 GiB	2.09×