Is granite-4.0-h-tiny-base or llama-3-youko-8b smaller?

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

Which uses less memory at long context?

granite-4.0-h-tiny-base — its KV cache at 32K context is 16.0x smaller, because of how its attention layers cache.

Model comparison

granite-4.0-h-tiny-base vs llama-3-youko-8b

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: granite-4.0-h-tiny-base's KV cache at 32K is 16.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	granite-4.0-h-tiny-base	llama-3-youko-8b
Parameters	6.9B	8.0B
Architecture	granitehybrid	llama
Layers	40	32
Native context	131,072	8,192
Mixture of experts	yes, 64 experts	no
Quantizations published	15	2
Smallest quantization	2.41 GiB	5.34 GiB
Q4_K_M	3.94 GiB	—
Licence	apache-2.0	llama3

KV cache by context

the term that decides long-context viability

Context	granite-4.0-h-tiny-base	llama-3-youko-8b	Ratio
4,096	0.03 GiB	0.50 GiB	15.96×
8,192	0.06 GiB	1.00 GiB	15.98×
16,384	0.13 GiB	2.00 GiB	15.99×
32,768	0.25 GiB	4.00 GiB	16.00×
65,536	0.50 GiB	8.00 GiB	16.00×
131,072	1.00 GiB	16.00 GiB	16.00×