Model comparison
Qwen3.5-0.8B-Base vs Unlimited-OCR
These two publish different quantization sets; the table below has the exact sizes.
From the file· summed bytes, KV per layer
Side by side
| Qwen3.5-0.8B-Base | Unlimited-OCR | |
|---|---|---|
| Parameters | 873M | 3.3B |
| Architecture | qwen35 | deepseek2-ocr |
| Layers | 24 | 12 |
| Native context | 262,144 | 32,768 |
| Mixture of experts | no | yes, 64 experts |
| Quantizations published | 3 | 21 |
| Smallest quantization | 0.52 GiB | 1.15 GiB |
| Q4_K_M | — | 1.82 GiB |
| Licence | apache-2.0 | mit |
KV cache by context
the term that decides long-context viability
| Context | Qwen3.5-0.8B-Base | 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 | — | — |