Is OLMo-2-1124-7B-Instruct 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 4.0x smaller, because of how its attention layers cache.

Model comparison

OLMo-2-1124-7B-Instruct 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 4.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	OLMo-2-1124-7B-Instruct	llama-3-youko-8b
Parameters	7.3B	8.0B
Architecture	olmo2	llama
Layers	32	32
Native context	4,096	8,192
Mixture of experts	no	no
Quantizations published	20	2
Smallest quantization	2.49 GiB	5.34 GiB
Q4_K_M	4.16 GiB	—
Licence	apache-2.0	llama3

KV cache by context

the term that decides long-context viability

Context	OLMo-2-1124-7B-Instruct	llama-3-youko-8b	Ratio
4,096	2.00 GiB	0.50 GiB	4.00×
8,192	4.00 GiB	1.00 GiB	4.00×
16,384	8.00 GiB	2.00 GiB	4.00×
32,768	16.00 GiB	4.00 GiB	4.00×
65,536	32.00 GiB	8.00 GiB	4.00×
131,072	64.00 GiB	16.00 GiB	4.00×