Model comparison

Unlimited-OCR vs Qwen3-VL-2B-Instruct

At Q4_K_M, Qwen3-VL-2B-Instruct is the smaller download — 1,107,409,952 bytes against 1,950,321,792.

From the file· summed bytes, KV per layer

Side by side

Unlimited-OCRQwen3-VL-2B-Instruct
Parameters3.3B2.1B
Architecturedeepseek2-ocrqwen3vl
Layers1228
Native context32,768262,144
Mixture of expertsyes, 64 expertsno
Quantizations published2146
Smallest quantization1.15 GiB0.50 GiB
Q4_K_M1.82 GiB1.03 GiB
Licencemitapache-2.0

KV cache by context

the term that decides long-context viability
ContextUnlimited-OCRQwen3-VL-2B-InstructRatio
4,0960.44 GiB
8,1920.88 GiB
16,3841.75 GiB
32,7683.50 GiB
65,5367.00 GiB
131,07214.00 GiB