Model comparison

Llama-3_1-Nemotron-51B-Instruct vs Qwen3-Coder-30B-A3B-Instruct

At Q4_K_M, Qwen3-Coder-30B-A3B-Instruct is the smaller download — 18,556,689,568 bytes against 31,037,307,136. At long context the gap widens: Qwen3-Coder-30B-A3B-Instruct's KV cache at 32K is 26.7× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

Llama-3_1-Nemotron-51B-InstructQwen3-Coder-30B-A3B-Instruct
Parameters51.5B30.5B
Architecturedeciqwen3moe
Layers8048
Native context131,072262,144
Mixture of expertsnoyes, 128 experts
Quantizations published2546
Smallest quantization13.07 GiB7.46 GiB
Q4_K_M28.91 GiB17.28 GiB
Licenceotherapache-2.0

KV cache by context

the term that decides long-context viability
ContextLlama-3_1-Nemotron-51B-InstructQwen3-Coder-30B-A3B-InstructRatio
4,09610.00 GiB0.38 GiB26.67×
8,19220.00 GiB0.75 GiB26.67×
16,38440.00 GiB1.50 GiB26.67×
32,76880.00 GiB3.00 GiB26.67×
65,536160.00 GiB6.00 GiB26.67×
131,072320.00 GiB12.00 GiB26.67×
Llama-3_1-Nemotron-51B-Instruct vs Qwen3-Coder-30B-A3B-Instruct — size, memory and hardware fit — ossmodeldb