Is Gemma4_E2B_Abliterated_Baked_HF_Ready or Qwen3-8B smaller?

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

Which uses less memory at long context?

Gemma4_E2B_Abliterated_Baked_HF_Ready — its KV cache at 32K context is 18.3x smaller, because of how its attention layers cache.

Model comparison

Gemma4_E2B_Abliterated_Baked_HF_Ready vs Qwen3-8B

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: Gemma4_E2B_Abliterated_Baked_HF_Ready's KV cache at 32K is 18.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Gemma4_E2B_Abliterated_Baked_HF_Ready	Qwen3-8B
Parameters	5.1B	8.2B
Architecture	gemma4	qwen3
Layers	35	36
Native context	131,072	40,960
Mixture of experts	no	no
Quantizations published	24	51
Smallest quantization	2.16 GiB	2.12 GiB
Q4_K_M	—	4.68 GiB
Licence	gemma	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Gemma4_E2B_Abliterated_Baked_HF_Ready	Qwen3-8B	Ratio
4,096	0.05 GiB	0.56 GiB	10.29×
8,192	0.08 GiB	1.13 GiB	13.71×
16,384	0.14 GiB	2.25 GiB	16.46×
32,768	0.25 GiB	4.50 GiB	18.29×
65,536	0.46 GiB	9.00 GiB	19.36×
131,072	0.90 GiB	18.00 GiB	19.95×