Model comparison

nsfwvision-qwen3-vl-8b-v3-safetensors vs Qwen3-30B-A3B-Thinking-2507

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: Qwen3-30B-A3B-Thinking-2507's KV cache at 32K is 1.5× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

nsfwvision-qwen3-vl-8b-v3-safetensorsQwen3-30B-A3B-Thinking-2507
Parameters8.8B30.5B
Architectureqwen3vlqwen3moe
Layers3648
Native context262,144262,144
Mixture of expertsnoyes, 128 experts
Quantizations published151
Smallest quantization8.11 GiB7.05 GiB
Q4_K_M—17.28 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
Contextnsfwvision-qwen3-vl-8b-v3-safetensorsQwen3-30B-A3B-Thinking-2507Ratio
4,0960.56 GiB0.38 GiB1.50×
8,1921.13 GiB0.75 GiB1.50×
16,3842.25 GiB1.50 GiB1.50×
32,7684.50 GiB3.00 GiB1.50×
65,5369.00 GiB6.00 GiB1.50×
131,07218.00 GiB12.00 GiB1.50×