Model comparison

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

At Q4_K_M, Qwen3-Coder-30B-A3B-Instruct is the smaller download — 18,556,689,568 bytes against 48,487,031,968.

From the file· summed bytes, KV per layer

Side by side

Qwen3-Coder-30B-A3B-InstructQwen3-Coder-Next
Parameters30.5B79.7B
Architectureqwen3moeqwen3next
Layers4848
Native context262,144262,144
Mixture of expertsyes, 128 expertsyes, 512 experts
Quantizations published4661
Smallest quantization7.46 GiB15.44 GiB
Q4_K_M17.28 GiB45.16 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen3-Coder-30B-A3B-InstructQwen3-Coder-NextRatio
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×