Model comparison

Qwen3-Coder-30B-A3B-Instruct vs Qwen3-16B-A3B

At Q4_K_M, Qwen3-16B-A3B is the smaller download — 9,754,940,096 bytes against 18,556,689,568.

From the file· summed bytes, KV per layer

Side by side

Qwen3-Coder-30B-A3B-InstructQwen3-16B-A3B
Parameters30.5B16.0B
Architectureqwen3moeqwen3moe
Layers4848
Native context262,14440,960
Mixture of expertsyes, 128 expertsyes, 64 experts
Quantizations published4646
Smallest quantization7.46 GiB4.12 GiB
Q4_K_M17.28 GiB9.08 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen3-Coder-30B-A3B-InstructQwen3-16B-A3BRatio
4,0960.38 GiB0.38 GiB1.00×
8,1920.75 GiB0.75 GiB1.00×
16,3841.50 GiB1.50 GiB1.00×
32,7683.00 GiB3.00 GiB1.00×
65,5366.00 GiB6.00 GiB1.00×
131,07212.00 GiB12.00 GiB1.00×
Qwen3-Coder-30B-A3B-Instruct vs Qwen3-16B-A3B — size, memory and hardware fit — ossmodeldb