Is v6-Finch-14B-HF or Qwen3.8-27B smaller?

v6-Finch-14B-HF is smaller at Q4_K_M: 8.17 GiB against 15.66 GiB.

Which uses less memory at long context?

Qwen3.8-27B — its KV cache at 32K context is 15.2x smaller, because of how its attention layers cache.

Model comparison

v6-Finch-14B-HF vs Qwen3.8-27B

At Q4_K_M, v6-Finch-14B-HF is the smaller download — 8,767,898,176 bytes against 16,810,714,336. At long context the gap widens: Qwen3.8-27B's KV cache at 32K is 15.2× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	v6-Finch-14B-HF	Qwen3.8-27B
Parameters	14.1B	27.8B
Architecture	rwkv6	qwen35
Layers	61	64
Native context	—	262,144
Mixture of experts	no	no
Quantizations published	20	22
Smallest quantization	5.10 GiB	8.39 GiB
Q4_K_M	8.17 GiB	15.66 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	v6-Finch-14B-HF	Qwen3.8-27B	Ratio
4,096	3.81 GiB	0.25 GiB	15.24×
8,192	7.63 GiB	0.50 GiB	15.24×
16,384	15.25 GiB	1.00 GiB	15.25×
32,768	30.50 GiB	2.00 GiB	15.25×
65,536	61.00 GiB	4.00 GiB	15.25×
131,072	122.00 GiB	8.00 GiB	15.25×