Model comparison

Qwen3-VL-Reranker-2B vs Qwen3-1.7B

At Q4_K_M, Qwen3-1.7B is the smaller download — 1,107,409,472 bytes against 1,107,410,784.

From the file· summed bytes, KV per layer

Side by side

Qwen3-VL-Reranker-2BQwen3-1.7B
Parameters2.1B2.0B
Architectureqwen3vlqwen3
Layers2828
Native context262,14440,960
Mixture of expertsnono
Quantizations published3648
Smallest quantization0.48 GiB0.50 GiB
Q4_K_M1.03 GiB1.03 GiB
Licenceapache-2.0—

KV cache by context

the term that decides long-context viability
ContextQwen3-VL-Reranker-2BQwen3-1.7BRatio
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×
Qwen3-VL-Reranker-2B vs Qwen3-1.7B — size, memory and hardware fit — ossmodeldb