Model comparison

Nanonets-OCR-s vs Qwen3-VL-2B-Instruct

At Q4_K_M, Qwen3-VL-2B-Instruct is the smaller download — 1,107,409,952 bytes against 1,929,900,800. At long context the gap widens: Nanonets-OCR-s's KV cache at 32K is 3.1× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

Nanonets-OCR-sQwen3-VL-2B-Instruct
Parameters3.8B2.1B
Architectureqwen2vlqwen3vl
Layers3628
Native context128,000262,144
Mixture of expertsnono
Quantizations published5646
Smallest quantization0.74 GiB0.50 GiB
Q4_K_M1.80 GiB1.03 GiB
Licenceapache-2.0

KV cache by context

the term that decides long-context viability
ContextNanonets-OCR-sQwen3-VL-2B-InstructRatio
4,0960.14 GiB0.44 GiB3.11×
8,1920.28 GiB0.88 GiB3.11×
16,3840.56 GiB1.75 GiB3.11×
32,7681.13 GiB3.50 GiB3.11×
65,5362.25 GiB7.00 GiB3.11×
131,0724.50 GiB14.00 GiB3.11×