Model comparison
Qwen3.5-2B-heretic vs Unlimited-OCR
At Q4_K_M, Qwen3.5-2B-heretic is the smaller download — 1,274,396,576 bytes against 1,950,321,792.
From the file· summed bytes, KV per layer
Side by side
| Qwen3.5-2B-heretic | Unlimited-OCR | |
|---|---|---|
| Parameters | 2.2B | 3.3B |
| Architecture | clip | deepseek2-ocr |
| Layers | 24 | 12 |
| Native context | 262,144 | 32,768 |
| Mixture of experts | no | yes, 64 experts |
| Quantizations published | 6 | 21 |
| Smallest quantization | 0.51 GiB | 1.15 GiB |
| Q4_K_M | 1.19 GiB | 1.82 GiB |
| Licence | apache-2.0 | mit |
KV cache by context
the term that decides long-context viability
| Context | Qwen3.5-2B-heretic | Unlimited-OCR | Ratio |
|---|---|---|---|
| 4,096 | 0.05 GiB | — | — |
| 8,192 | 0.09 GiB | — | — |
| 16,384 | 0.19 GiB | — | — |
| 32,768 | 0.38 GiB | — | — |
| 65,536 | 0.75 GiB | — | — |
| 131,072 | 1.50 GiB | — | — |