Is Firefly-v4 or llama-3-youko-8b smaller?

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

Which uses less memory at long context?

Firefly-v4 — its KV cache at 32K context is 16.3x smaller, because of how its attention layers cache.

Model comparison

Firefly-v4 vs llama-3-youko-8b

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: Firefly-v4's KV cache at 32K is 16.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Firefly-v4	llama-3-youko-8b
Parameters	5.1B	8.0B
Architecture	gemma4	llama
Layers	35	32
Native context	131,072	8,192
Mixture of experts	no	no
Quantizations published	27	2
Smallest quantization	2.78 GiB	5.34 GiB
Q4_K_M	3.19 GiB	—
Licence	other	llama3

KV cache by context

the term that decides long-context viability

Context	Firefly-v4	llama-3-youko-8b	Ratio
4,096	0.05 GiB	0.50 GiB	9.14×
8,192	0.08 GiB	1.00 GiB	12.19×
16,384	0.14 GiB	2.00 GiB	14.63×
32,768	0.25 GiB	4.00 GiB	16.25×
65,536	0.46 GiB	8.00 GiB	17.21×
131,072	0.90 GiB	16.00 GiB	17.73×