Is Qwen3-Zero-Coder-Reasoning-V2-0.8B or embeddinggemma-300m smaller?

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

Which uses less memory at long context?

embeddinggemma-300m — its KV cache at 32K context is 36.3x smaller, because of how its attention layers cache.

Model comparison

Qwen3-Zero-Coder-Reasoning-V2-0.8B vs embeddinggemma-300m

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: embeddinggemma-300m's KV cache at 32K is 36.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3-Zero-Coder-Reasoning-V2-0.8B	embeddinggemma-300m
Parameters	816M	303M
Architecture	qwen3	gemma-embedding
Layers	42	24
Native context	40,960	2,048
Mixture of experts	no	no
Quantizations published	26	10
Smallest quantization	0.24 GiB	0.26 GiB
Q4_K_M	—	—
Licence	apache-2.0	—

KV cache by context

the term that decides long-context viability

Context	Qwen3-Zero-Coder-Reasoning-V2-0.8B	embeddinggemma-300m	Ratio
4,096	0.66 GiB	0.04 GiB	18.67×
8,192	1.31 GiB	0.05 GiB	25.85×
16,384	2.63 GiB	0.08 GiB	32.00×
32,768	5.25 GiB	0.14 GiB	36.32×
65,536	10.50 GiB	0.27 GiB	38.96×
131,072	21.00 GiB	0.52 GiB	40.42×