Is deepseek-r1-distill-qwen-1.5b-unsloth-bnb-4bit or Llama-3.1-8B-Instruct smaller?

deepseek-r1-distill-qwen-1.5b-unsloth-bnb-4bit is smaller at Q4_K_M: 1.04 GiB against 4.58 GiB.

Which uses less memory at long context?

deepseek-r1-distill-qwen-1.5b-unsloth-bnb-4bit — its KV cache at 32K context is 4.6x smaller, because of how its attention layers cache.

Model comparison

deepseek-r1-distill-qwen-1.5b-unsloth-bnb-4bit vs Llama-3.1-8B-Instruct

At Q4_K_M, deepseek-r1-distill-qwen-1.5b-unsloth-bnb-4bit is the smaller download — 1,117,320,640 bytes against 4,920,739,168. At long context the gap widens: deepseek-r1-distill-qwen-1.5b-unsloth-bnb-4bit's KV cache at 32K is 4.6× 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-1.5b-unsloth-bnb-4bit	Llama-3.1-8B-Instruct
Parameters	1.8B	8.0B
Architecture	qwen2	llama
Layers	28	32
Native context	131,072	131,072
Mixture of experts	no	no
Quantizations published	2	45
Smallest quantization	1.04 GiB	2.02 GiB
Q4_K_M	1.04 GiB	4.58 GiB
Licence	apache-2.0	llama3.1

KV cache by context

the term that decides long-context viability

Context	deepseek-r1-distill-qwen-1.5b-unsloth-bnb-4bit	Llama-3.1-8B-Instruct	Ratio
4,096	0.11 GiB	0.50 GiB	4.57×
8,192	0.22 GiB	1.00 GiB	4.57×
16,384	0.44 GiB	2.00 GiB	4.57×
32,768	0.88 GiB	4.00 GiB	4.57×
65,536	1.75 GiB	8.00 GiB	4.57×
131,072	3.50 GiB	16.00 GiB	4.57×