Model comparison

Openprose-2-Flash vs Qwen3-30B-A3B-Thinking-2507

At Q4_K_M, Openprose-2-Flash is the smaller download — 5,780,091,296 bytes against 18,556,685,824. At long context the gap widens: Openprose-2-Flash's KV cache at 32K is 3.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

Openprose-2-FlashQwen3-30B-A3B-Thinking-2507
Parameters9.7B30.5B
Architectureqwen35qwen3moe
Layers3248
Native context262,144262,144
Mixture of expertsnoyes, 128 experts
Quantizations published2751
Smallest quantization3.65 GiB7.05 GiB
Q4_K_M5.38 GiB17.28 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextOpenprose-2-FlashQwen3-30B-A3B-Thinking-2507Ratio
4,0960.13 GiB0.38 GiB3.00×
8,1920.25 GiB0.75 GiB3.00×
16,3840.50 GiB1.50 GiB3.00×
32,7681.00 GiB3.00 GiB3.00×
65,5362.00 GiB6.00 GiB3.00×
131,0724.00 GiB12.00 GiB3.00×
Openprose-2-Flash vs Qwen3-30B-A3B-Thinking-2507 — size, memory and hardware fit — ossmodeldb