Model comparison

Qwen3-Reranker-0.6B vs Qwen3-0.6B

At Q4_K_M, Qwen3-Reranker-0.6B is the smaller download — 396,474,720 bytes against 396,705,472.

From the file· summed bytes, KV per layer

Side by side

Qwen3-Reranker-0.6BQwen3-0.6B
Parameters596M752M
Architectureqwen3qwen3
Layers2828
Native context40,96040,960
Mixture of expertsnono
Quantizations published2244
Smallest quantization0.28 GiB0.20 GiB
Q4_K_M0.37 GiB0.37 GiB
Licenceapache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen3-Reranker-0.6BQwen3-0.6BRatio
4,0960.44 GiB0.44 GiB1.00×
8,1920.88 GiB0.88 GiB1.00×
16,3841.75 GiB1.75 GiB1.00×
32,7683.50 GiB3.50 GiB1.00×
65,5367.00 GiB7.00 GiB1.00×
131,07214.00 GiB14.00 GiB1.00×