Model comparison

Qwen3-4B-Instruct vs Qwen3-8B

At Q4_K_M, Qwen3-4B-Instruct is the smaller download — 2,497,278,784 bytes against 5,027,783,488.

From the file· summed bytes, KV per layer

Side by side

Qwen3-4B-InstructQwen3-8B
Parameters4.0B8.2B
Architectureqwen3qwen3
Layers36
Native context40,960
Mixture of expertsnono
Quantizations published851
Smallest quantization1.55 GiB2.12 GiB
Q4_K_M2.33 GiB4.68 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen3-4B-InstructQwen3-8BRatio
4,0960.56 GiB
8,1921.13 GiB
16,3842.25 GiB
32,7684.50 GiB
65,5369.00 GiB
131,07218.00 GiB