Model comparison
Ornith-1.0-9B-Uncensored vs Qwen3.6-27B
At Q4_K_M, Ornith-1.0-9B-Uncensored is the smaller download — 5,629,108,416 bytes against 16,547,397,888. At long context the gap widens: Ornith-1.0-9B-Uncensored's KV cache at 32K is 2.0× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| Ornith-1.0-9B-Uncensored | Qwen3.6-27B | |
|---|---|---|
| Parameters | 9.4B | 27.8B |
| Architecture | qwen35 | qwen35 |
| Layers | 32 | 64 |
| Native context | 262,144 | 262,144 |
| Mixture of experts | no | no |
| Quantizations published | 4 | 40 |
| Smallest quantization | 5.24 GiB | 8.74 GiB |
| Q4_K_M | 5.24 GiB | 15.41 GiB |
| Licence | mit | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | Ornith-1.0-9B-Uncensored | Qwen3.6-27B | Ratio |
|---|---|---|---|
| 4,096 | 0.13 GiB | 0.25 GiB | 2.00× |
| 8,192 | 0.25 GiB | 0.50 GiB | 2.00× |
| 16,384 | 0.50 GiB | 1.00 GiB | 2.00× |
| 32,768 | 1.00 GiB | 2.00 GiB | 2.00× |
| 65,536 | 2.00 GiB | 4.00 GiB | 2.00× |
| 131,072 | 4.00 GiB | 8.00 GiB | 2.00× |