Is Tema_Q-X5-12B-Thinking or llama-3-youko-8b smaller?

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

Which uses less memory at long context?

Tema_Q-X5-12B-Thinking — its KV cache at 32K context is 1.6x smaller, because of how its attention layers cache.

Model comparison

Tema_Q-X5-12B-Thinking vs llama-3-youko-8b

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: Tema_Q-X5-12B-Thinking's KV cache at 32K is 1.6× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Tema_Q-X5-12B-Thinking	llama-3-youko-8b
Parameters	12.0B	8.0B
Architecture	gemma4	llama
Layers	48	32
Native context	131,072	8,192
Mixture of experts	no	no
Quantizations published	35	2
Smallest quantization	2.78 GiB	5.34 GiB
Q4_K_M	6.87 GiB	—
Licence	—	llama3

KV cache by context

the term that decides long-context viability

Context	Tema_Q-X5-12B-Thinking	llama-3-youko-8b	Ratio
4,096	0.72 GiB	0.50 GiB	1.44×
8,192	0.97 GiB	1.00 GiB	1.03×
16,384	1.47 GiB	2.00 GiB	1.36×
32,768	2.47 GiB	4.00 GiB	1.62×
65,536	4.47 GiB	8.00 GiB	1.79×
131,072	8.47 GiB	16.00 GiB	1.89×