Model comparison

Qwen3-Coder-30B-A3B-Instruct vs LocalAI-functioncall-qwen2.5-7b-v0.5

At Q4_K_M, LocalAI-functioncall-qwen2.5-7b-v0.5 is the smaller download — 4,683,074,048 bytes against 18,556,689,568. At long context the gap widens: LocalAI-functioncall-qwen2.5-7b-v0.5's KV cache at 32K is 1.7× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

Qwen3-Coder-30B-A3B-InstructLocalAI-functioncall-qwen2.5-7b-v0.5
Parameters30.5B7.6B
Architectureqwen3moeqwen2
Layers4828
Native context262,14432,768
Mixture of expertsyes, 128 expertsno
Quantizations published461
Smallest quantization7.46 GiB4.36 GiB
Q4_K_M17.28 GiB4.36 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen3-Coder-30B-A3B-InstructLocalAI-functioncall-qwen2.5-7b-v0.5Ratio
4,0960.38 GiB0.22 GiB1.71×
8,1920.75 GiB0.44 GiB1.71×
16,3841.50 GiB0.88 GiB1.71×
32,7683.00 GiB1.75 GiB1.71×
65,5366.00 GiB3.50 GiB1.71×
131,07212.00 GiB7.00 GiB1.71×