Is Qwen2.5-Coder-0.5B-Instruct-abliterated 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 2.6x smaller, because of how its attention layers cache.

Model comparison

Qwen2.5-Coder-0.5B-Instruct-abliterated 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 2.6× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen2.5-Coder-0.5B-Instruct-abliterated	embeddinggemma-300m
Parameters	494M	303M
Architecture	qwen2	gemma-embedding
Layers	24	24
Native context	32,768	2,048
Mixture of experts	no	no
Quantizations published	14	10
Smallest quantization	0.32 GiB	0.26 GiB
Q4_K_M	0.37 GiB	—
Licence	apache-2.0	—

KV cache by context

the term that decides long-context viability

Context	Qwen2.5-Coder-0.5B-Instruct-abliterated	embeddinggemma-300m	Ratio
4,096	0.05 GiB	0.04 GiB	1.33×
8,192	0.09 GiB	0.05 GiB	1.85×
16,384	0.19 GiB	0.08 GiB	2.29×
32,768	0.38 GiB	0.14 GiB	2.59×
65,536	0.75 GiB	0.27 GiB	2.78×
131,072	1.50 GiB	0.52 GiB	2.89×