Is Llama-3.3-70B-Instruct or Qwen3.8-27B smaller?

Qwen3.8-27B is smaller at Q4_K_M: 15.66 GiB against 39.60 GiB.

Which uses less memory at long context?

Qwen3.8-27B — its KV cache at 32K context is 5.0x smaller, because of how its attention layers cache.

Model comparison

Llama-3.3-70B-Instruct vs Qwen3.8-27B

At Q4_K_M, Qwen3.8-27B is the smaller download — 16,810,714,336 bytes against 42,520,398,432. At long context the gap widens: Qwen3.8-27B's KV cache at 32K is 5.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Llama-3.3-70B-Instruct	Qwen3.8-27B
Parameters	70.6B	27.8B
Architecture	llama	qwen35
Layers	80	64
Native context	131,072	262,144
Mixture of experts	no	no
Quantizations published	52	22
Smallest quantization	14.77 GiB	8.39 GiB
Q4_K_M	39.60 GiB	15.66 GiB
Licence	—	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Llama-3.3-70B-Instruct	Qwen3.8-27B	Ratio
4,096	1.25 GiB	0.25 GiB	5.00×
8,192	2.50 GiB	0.50 GiB	5.00×
16,384	5.00 GiB	1.00 GiB	5.00×
32,768	10.00 GiB	2.00 GiB	5.00×
65,536	20.00 GiB	4.00 GiB	5.00×
131,072	40.00 GiB	8.00 GiB	5.00×