Is HopCoder-Mini-35B-A3B-VL36 or Qwen3.6-27B smaller?

Qwen3.6-27B is smaller at Q4_K_M: 15.41 GiB against 19.71 GiB.

Which uses less memory at long context?

HopCoder-Mini-35B-A3B-VL36 — its KV cache at 32K context is 3.2x smaller, because of how its attention layers cache.

Model comparison

HopCoder-Mini-35B-A3B-VL36 vs Qwen3.6-27B

At Q4_K_M, Qwen3.6-27B is the smaller download — 16,547,397,888 bytes against 21,166,754,048. At long context the gap widens: HopCoder-Mini-35B-A3B-VL36's KV cache at 32K is 3.2× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	HopCoder-Mini-35B-A3B-VL36	Qwen3.6-27B
Parameters	35.1B	27.8B
Architecture	—	qwen35
Layers	40	64
Native context	262,144	262,144
Mixture of experts	yes, 256 experts	no
Quantizations published	15	40
Smallest quantization	8.82 GiB	8.74 GiB
Q4_K_M	19.71 GiB	15.41 GiB
Licence	other	apache-2.0

KV cache by context

the term that decides long-context viability

Context	HopCoder-Mini-35B-A3B-VL36	Qwen3.6-27B	Ratio
4,096	0.08 GiB	0.25 GiB	3.20×
8,192	0.16 GiB	0.50 GiB	3.20×
16,384	0.31 GiB	1.00 GiB	3.20×
32,768	0.63 GiB	2.00 GiB	3.20×
65,536	1.25 GiB	4.00 GiB	3.20×
131,072	2.50 GiB	8.00 GiB	3.20×