Is DeepSeek-R1-Distill-Qwen-14B-abliterated-v2 or Qwen3-Coder-30B-A3B-Instruct smaller?

DeepSeek-R1-Distill-Qwen-14B-abliterated-v2 is smaller at Q4_K_M: 8.37 GiB against 17.28 GiB.

Which uses less memory at long context?

Qwen3-Coder-30B-A3B-Instruct — its KV cache at 32K context is 2.0x smaller, because of how its attention layers cache.

Model comparison

DeepSeek-R1-Distill-Qwen-14B-abliterated-v2 vs Qwen3-Coder-30B-A3B-Instruct

At Q4_K_M, DeepSeek-R1-Distill-Qwen-14B-abliterated-v2 is the smaller download — 8,988,110,432 bytes against 18,556,689,568. At long context the gap widens: Qwen3-Coder-30B-A3B-Instruct's KV cache at 32K is 2.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	DeepSeek-R1-Distill-Qwen-14B-abliterated-v2	Qwen3-Coder-30B-A3B-Instruct
Parameters	14.8B	30.5B
Architecture	qwen2	qwen3moe
Layers	48	48
Native context	131,072	262,144
Mixture of experts	no	yes, 128 experts
Quantizations published	46	46
Smallest quantization	3.36 GiB	7.46 GiB
Q4_K_M	8.37 GiB	17.28 GiB
Licence	—	apache-2.0

KV cache by context

the term that decides long-context viability

Context	DeepSeek-R1-Distill-Qwen-14B-abliterated-v2	Qwen3-Coder-30B-A3B-Instruct	Ratio
4,096	0.75 GiB	0.38 GiB	2.00×
8,192	1.50 GiB	0.75 GiB	2.00×
16,384	3.00 GiB	1.50 GiB	2.00×
32,768	6.00 GiB	3.00 GiB	2.00×
65,536	12.00 GiB	6.00 GiB	2.00×
131,072	24.00 GiB	12.00 GiB	2.00×