Is Pantheon-Reasoning-26B-A4B-1.1-heretic or Qwen3-Coder-30B-A3B-Instruct smaller?

Pantheon-Reasoning-26B-A4B-1.1-heretic is smaller at Q4_K_M: 16.03 GiB against 17.28 GiB.

Which uses less memory at long context?

Pantheon-Reasoning-26B-A4B-1.1-heretic — its KV cache at 32K context is 1.9x smaller, because of how its attention layers cache.

Model comparison

Pantheon-Reasoning-26B-A4B-1.1-heretic vs Qwen3-Coder-30B-A3B-Instruct

At Q4_K_M, Pantheon-Reasoning-26B-A4B-1.1-heretic is the smaller download — 17,211,252,736 bytes against 18,556,689,568. At long context the gap widens: Pantheon-Reasoning-26B-A4B-1.1-heretic's KV cache at 32K is 1.9× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Pantheon-Reasoning-26B-A4B-1.1-heretic	Qwen3-Coder-30B-A3B-Instruct
Parameters	26.5B	30.5B
Architecture	gemma4	qwen3moe
Layers	30	48
Native context	262,144	262,144
Mixture of experts	yes, 128 experts	yes, 128 experts
Quantizations published	34	46
Smallest quantization	7.95 GiB	7.46 GiB
Q4_K_M	16.03 GiB	17.28 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Pantheon-Reasoning-26B-A4B-1.1-heretic	Qwen3-Coder-30B-A3B-Instruct	Ratio
4,096	0.45 GiB	0.38 GiB	1.20×
8,192	0.61 GiB	0.75 GiB	1.24×
16,384	0.92 GiB	1.50 GiB	1.63×
32,768	1.54 GiB	3.00 GiB	1.94×
65,536	2.79 GiB	6.00 GiB	2.15×
131,072	5.29 GiB	12.00 GiB	2.27×