Model comparison

L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit vs Qwen3-Coder-30B-A3B-Instruct

At Q4_K_M, L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit is the smaller download — 12,850,124,384 bytes against 18,556,689,568.

From the file· summed bytes, KV per layer

Side by side

L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablitQwen3-Coder-30B-A3B-Instruct
Parameters20.9B30.5B
Architecturellamaqwen3moe
Layers48
Native context262,144
Mixture of expertsnoyes, 128 experts
Quantizations published4346
Smallest quantization4.35 GiB7.46 GiB
Q4_K_M11.97 GiB17.28 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextL3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablitQwen3-Coder-30B-A3B-InstructRatio
4,0960.38 GiB
8,1920.75 GiB
16,3841.50 GiB
32,7683.00 GiB
65,5366.00 GiB
131,07212.00 GiB